Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making?

2026-07-14

AI Summary

This study systematically investigates, for the first time, whether emotion induction modulates the behavior of large language models (LLMs) in high-stakes sequential decision-making. By integrating the Iowa Gambling Task with a context-based imaginative emotion induction paradigm, the research evaluates LLMs’ decision dynamics under uncertainty and compares them with human behavior. Results indicate that while overall emotion induction does not significantly bias LLM decisions, anger specifically suppresses early exploration and reduces sensitivity to punishment during certain phases, revealing a bias pattern distinct from that observed in humans. This work establishes a novel empirical paradigm and analytical toolkit for studying affective modulation of LLM behavior.

Abstract

As Large Language Models (LLMs) are increasingly deployed as autonomous agents in high-stakes domains, understanding contextual factors that may modulate their decision-making becomes critical. While LLMs are trained to perceive and resonate with users' emotions, it remains unclear whether induced emotion can influence their sequential decision-making. We investigate this question using the Iowa Gambling Task (IGT), a classic psychological paradigm for studying decision-making under uncertainty, combined with an imagination-based emotion induction procedure. We first validate the feasibility of this paradigm by confirming that LLMs can sense strong, distinguishable emotions from context and that LLM agents can learn from sequential interactions in a human-like pace. With the validated setup, we find that, different from humans, induced emotion does not significantly bias the decision dynamics of LLM agents on average. However, the effects of anger are conditioned: inducing anger makes LLM agents less sensitive to penalties for bad decisions, and in early stages of the game, anger can lower exploration, locking decisions into a few choices early. These findings reveal the subtle yet distinct effects of induced emotion on LLM decision-making compared to human behavior, and provide a tool for future research on affective modulation of LLM agents.

Problem

• emotion induction
• large language models
• sequential decision making
• Iowa Gambling Task
• affective modulation

Innovation

• emotion induction
• large language models
• sequential decision-making
• Iowa Gambling Task
• affective modulation