Human Emotion Knowledge Representation Emerges in Large Language Model and Supports Discrete Emotion Inference

by   Ming Li, et al.

How humans infer discrete emotions is a fundamental research question in the field of psychology. While conceptual knowledge about emotions (emotion knowledge) has been suggested to be essential for emotion inference, evidence to date is mostly indirect and inconclusive. As the large language models (LLMs) have been shown to support effective representations of various human conceptual knowledge, the present study further employed artificial neurons in LLMs to investigate the mechanism of human emotion inference. With artificial neurons activated by prompts, the LLM (RoBERTa) demonstrated a similar conceptual structure of 27 discrete emotions as that of human behaviors. Furthermore, the LLM-based conceptual structure revealed a human-like reliance on 14 underlying conceptual attributes of emotions for emotion inference. Most importantly, by manipulating attribute-specific neurons, we found that the corresponding LLM's emotion inference performance deteriorated, and the performance deterioration was correlated to the effectiveness of representations of the conceptual attributes on the human side. Our findings provide direct evidence for the emergence of emotion knowledge representation in large language models and suggest its casual support for discrete emotion inference.


page 24

page 25

page 26

page 30

page 31

page 32

page 33

page 34


An Appraisal-Based Chain-Of-Emotion Architecture for Affective Language Model Game Agents

The development of believable, natural, and interactive digital artifici...

Does Conceptual Representation Require Embodiment? Insights From Large Language Models

Recent advances in large language models (LLM) have the potential to she...

Simulation of Human and Artificial Emotion (SHArE)

The framework for Simulation of Human and Artificial Emotion (SHArE) des...

Socratis: Are large multimodal models emotionally aware?

Existing emotion prediction benchmarks contain coarse emotion labels whi...

Behavioral estimates of conceptual structure are robust across tasks in humans but not large language models

Neural network models of language have long been used as a tool for deve...

CAKE: Compact and Accurate K-dimensional representation of Emotion

Inspired by works from the psychology community, we first study the link...

Unveiling Theory of Mind in Large Language Models: A Parallel to Single Neurons in the Human Brain

With their recent development, large language models (LLMs) have been fo...

Please sign up or login with your details

Forgot password? Click here to reset