AI with Emotions: Exploring Emotional Expressions in Large Language Models
Preprint
Abstract
The human-level performance of Large Language Models (LLMs) across various tasks has raised expectations for the potential of Artificial Intelligence (AI) to possess emotions someday. To explore the capability of current LLMs to express emotions in their outputs, we conducted an experiment using several LLMs (OpenAI GPT, Google Gemini, Meta Llama3, and Cohere Command R+) to role-play as agents answering questions with specified emotional states.We defined the emotional states using Russell's Circumplex model, a well-established framework that characterizes emotions along the sleepy-activated (arousal) and pleasure-displeasure (valence) axes. We chose this model for its simplicity, utilizing two continuous parameters, which allows for better controllability in applications involving continuous changes in emotional states. The responses generated were evaluated using a sentiment analysis model, independent of the LLMs, trained on the GoEmotions dataset. The evaluation showed that the emotional states of the generated answers were consistent with the specifications, demonstrating the LLMs' capability for emotional expression. This indicates the potential for LLM-based AI agents to simulate emotions, opening up a wide range of applications for emotion-based interactions, such as advisors or consultants who can provide advice or opinions with a personal touch.Keywords
All Related Versions
This publication has 29 references indexed in Scilit:
- Role play with large language modelsNature, 2023
- Emotional expression by artificial intelligence chatbots to improve customer satisfaction: Underlying mechanism and boundary conditionsTourism Management, 2023
- Affective state estimation based on Russell’s model and physiological measurementsScientific Reports, 2023
- ChatGPT: Jack of all trades, master of noneInformation Fusion, 2023
- Multimodal sentiment analysis: A systematic review of history, datasets, multimodal fusion methods, applications, challenges and future directionsInformation Fusion, 2022
- Music emotion recognition using recurrent neural networks and pretrained modelsJournal of Intelligent Information Systems, 2021
- A comprehensive survey on sentiment analysis: Approaches, challenges and trendsKnowledge-Based Systems, 2021
- Emotion expression and regulation in three cultures: Chinese, Japanese, and American preschoolers’ reactions to disappointmentJournal of Experimental Child Psychology, 2021
- Facial expressions and the ability to recognize emotions from the eyes or mouth: A comparison among old adults, young adults, and childrenThe Journal of Genetic Psychology, 2018
- Sentiment analysis algorithms and applications: A surveyAin Shams Engineering Journal, 2014