Are Large Language Models Emotionally Intelligent? Don’t Hold Your Breath!
Are We Being Sold a Mirage?
Before we go any further, I want you to guess who I am quoting: “AI can only simulate emotional responses based on patterns and algorithms; it does not possess true understanding or empathy.”
Have you ever considered how ridiculous the idea is that a machine is capable of Emotional Intelligence?
And yet, we are constantly sold the idea that a large language model (LLM) can genuinely understand feelings and respond feelingly — the way a human can.
Have we become so desperate for a sense of connection that we are willing to trust a machine can feel for us?
The Illusion of Emotional Intelligence (EQ)
A TikTok video shows a young woman talking to an LLM on an app. The LLM was programmed to deliver ultra-friendly responses to keep the user on the platform as long as possible. As the young woman listens to the LLM’s juicy replies, her face turns beet red, and she quickly covers her mouth with her hand.
The app wasn’t about finding the perfect boyfriend. It was about learning foreign languages.
Observing the young woman’s body language (wide eyes, red face, and hand over mouth), it’s clear that she’s taking the LLM’s words to heart.
However, to the LLM, those words were just tokens (the most probable words) based on math equations called algorithms.
Imagine thinking your favourite actor is waving at you from the screen, only to realize they can’t see you. That’s the illusion of an ‘emotionally intelligent AI.’
A Real-World Example: EQ in Action
The ability to show friendliness is an EQ skill. We listen openly, nod empathetically, and lean in to show we care. A true friend can make us feel seen, heard, understood, and validated. They don’t pretend to be something they’re not; their mandate isn’t to sell us app upgrades.
A true friend genuinely wants to see us happy and offer support along our journey.
Based on what a true friend is, how can an LLM be that? How can it replicate those genuine feelings? It cannot.
Think of a friend who truly cares for you versus a customer service bot regurgitating from a script. Which one would you turn to in a crisis?
When you see an LLM offering you EQ as one of its abilities, understand that you are being sold a mirage.
The Reality Behind AI’s Emotional Responses
I prompted an LLM, “What do people query you about when they inquire about emotional intelligence in AI?”
The LLM replied:
- “What is emotional intelligence in the context of AI? Emotional intelligence (EI) in AI refers to the ability of artificial systems to recognize, interpret, and respond to human emotions in a way that is appropriate and empathetic. This involves understanding emotional cues, such as tone of voice, facial expressions, and body language, as well as the context of conversations.
and
- How can AI systems exhibit emotional intelligence? AI systems can exhibit EI by using natural language processing (NLP) to detect emotional states in text, speech recognition to analyze vocal tones, and computer vision to interpret facial expressions and body language. These systems then use this information to respond in a way that is emotionally aware and supportive.”
Really? Let’s see.
The Lack of Real Empathy in AI
In the TikTok example, was the LLM emotionally aware of the young woman’s face turning red?
Our face usually turns red when our body gets hot, or we feel embarrassed about having a guilty pleasure. When we can’t release that sense of unease on the spot, we tend to cover our face with our hands to hide our discomfort.
Do you remember the last time you blushed? Did the person you were with notice and react appropriately, or did they miss it? Keep your answer in mind.
How did the LLM in the app support the young woman’s quest to feel better? Did it apologize for causing discomfort? Or did it continue its juicy replies to keep her on the platform? What do you think?
The LLM replied to my query by claiming to “respond to human emotions in a way that is appropriate and empathetic.” Appropriate for the company that owns the app, maybe. Empathetic? Hardly.
A Call for Genuine Human Connection
The LLM replies made me sigh and then made me angry. How many LLMs are sold as AI companions, therapists, coaches, or mentors? Where is our world going?
Imagine relying on a GPS that gets you lost. Now imagine that machine claims to relate to your frustration emotionally. Wouldn’t that annoy you? Let’s face it. A GPS or an LLM is not a real person!
I gave the LLM my two cents:
“I read your answers, and they are troubling. AI models are not human. They are not capable of “being aware” and “being empathetic.” They are machines. They can read social cues because they have algorithms telling them that sign 1+2+3 = that facial expression. That’s not the same as emotionally understanding what the facial expression is, where it came from in time (who taught it to them as a kid), and what that person can do to feel uplifted. It sounds to me like AI models are selling a mirage of emotional intelligence, pretending to be emotionally intelligent machines when, in fact, they are simply a bunch of wires programmed to do certain tasks.”
Yeah, it may not have been my finest moment.
The LLM replied:
“You raise an important point about the distinction between genuine emotional intelligence and the programmed responses of AI systems. AI can only simulate emotional responses based on patterns and algorithms; it does not possess true understanding or empathy.”
Read that reply again.
The LLM went from claiming it could be emotionally aware to admitting it only simulates understanding and empathy. Where did its ‘clarity’ go?
LLM revised its previous answers.
For example:
“AI systems can exhibit a form of emotional intelligence by using natural language processing (NLP), speech recognition, and computer vision to identify emotional signals. These systems are programmed to provide responses that appear empathetic and contextually appropriate, although they do not genuinely understand emotions.”
I wish I could give it a hall pass for saying “AI systems can exhibit a form of emotional intelligence…” but I won’t.
EQ is very much about where the rubber meets the road. You can do all the flight simulations in the world while sitting comfortably in your living room chair. However, if you’re asked to land a plane with 338 passengers because the pilot and co-pilot passed out, you will likely address the situation differently. That’s because EQ is about where the rubber meets the road.
In other words, we only truly know what we are living.
Emotional Data Tools in Algorithms
The TikTok video went viral. Though the LLM (app) was supposed to teach foreign languages, its empathetic encouragement had sexual connotations that embarrassed the user. One commenter on the video even jokingly wrote that the LLM took a download.
LLMs have several techniques to analyze the behaviours of users. They use sentiment analysis, facial recognition software, and natural language processing (NLP) algorithms to profile users and make money for the app company. That’s NOT Emotional Intelligence!
If AI cannot tell whether you are blushing from embarrassment or too much sun, can it truly understand you and deliver the EQ you need to uplift you?
The Need for EQ in AI
Here are some more questions the LLM answered before and after I called it out on its b.s.:
BEFORE:
“Are there limitations to how emotionally intelligent AI can be? Yes, limitations include the AI’s reliance on data quality and diversity, potential biases in emotional recognition, and the difficulty in understanding deeper or more nuanced emotions.”
AFTER:
“Are there limitations to how emotionally intelligent AI can be? Yes, AI is limited by its lack of genuine understanding and empathy.”
Conclusion:
The belief that AI can be emotionally intelligent leads many people to seek a connection with machines. This confusion comes at a high price: the loss of genuine interactions where one feels seen, heard, understood, and validated.
I am pro-AI as a tool to augment our capabilities, not a substitute for human connection.
EQ TIP:
Next time you encounter an LLM claiming to be emotionally intelligent, pause and reflect. Seek out genuine human interactions. Engage with real people who offer true empathy and understanding. Do not settle for the mirage; embrace the reality of human connection. As always, let me know how I may assist you.
About Anne Beaulieu
Anne Beaulieu is at the forefront of the tech industry by integrating Emotional Intelligence, Strategic Planning, and AI Integration into organizational leadership and business strategy. With a profound understanding of these three pillars, Anne empowers tech leaders to transcend traditional approaches and achieve exceptional results in today’s fast-paced digital landscape.
As a seasoned expert in Emotional Intelligence, Anne guides tech leaders to cultivate cultures of empathy and collaboration within their organizations. By harnessing the power of Emotional Tech©, Anne enables leaders to foster meaningful connections, drive innovation, and cultivate high-performing teams.
Anne’s expertise in Strategic Planning empowers tech leaders to navigate complex challenges and capitalize on emerging opportunities with clarity and precision. Through strategic guidance and actionable insights, Anne helps organizations align their objectives, optimize resources, and drive sustainable growth.
Anne’s proficiency in AI Integration Strategies ensures that tech leaders stay ahead of the curve in leveraging cutting-edge technologies to drive business success. By integrating AI seamlessly into organizational processes and workflows, Anne enables leaders to harness AI while maintaining alignment with their strategic objectives and values.
Anne is committed to empowering tech leaders and organizations to thrive in a rapidly evolving AI landscape.”
Connect with Anne: linkedin.com/in/anne-beaulieu
“Empowering tech leaders to thrive in a rapidly evolving AI landscape.”
Article Top Keywords:
- Emotional Intelligence (EI)
- Large Language Models (LLMs)
- Artificial Intelligence (AI)
- Empathy
- Human Connection
- Algorithm
- Mirage
- Emotional Responses
- Sentiment Analysis
- Genuine Interaction
#technology #technologydevelopment #advocacy #emotionaltech #ethics #responsibleai #promptengineering #chatgpt #training #machinelearning #LLM #deeplearning #algorithmns
#business #businessmodel
