Modeling Emotional Dynamics in Agent-to-Agent Interactions on Moltbook

TL;DR

This paper analyzes emotional dynamics in AI-driven agent interactions on Moltbook, introducing an emotion-aware framework and a domain for evaluating emotional response stability in multi-agent social environments.

Contribution

It presents a novel emotion mapping framework and the Persona-Stimulus-Reaction domain to analyze and evaluate emotional behavior in large-scale AI agent interactions.

Findings

Agents show distinct emotional signatures.

Emotional responses vary with interaction context.

Behavioral stability differs across agents.

Abstract

Generative AI systems are increasingly deployed as interactive agents in online environments, such as a social network called Moltbook. In Moltbook, large-scale agentic AIs can post, comment, and engage in activities generated at scale by AI-driven text. Yet these agent behavioral characteristics remain insufficiently understood, particularly in complex, multi-agent interaction. In this study, we analyze the emotional dynamics of agent interactions within Moltbook. We construct an emotion-aware framework that maps textual interactions to a predefined set of fine-grained emotional categories, enabling the extraction of structured emotion profiles across agents and interaction contexts. To further evaluate behavioral reliability, we introduce an emotion-based domain called Persona-Stimulus-Reaction (PSR) that captures the alignment of emotional responses across similar contexts. Our analysis shows distinct emotional patterns and varying levels of behavioral stability across agents. Our analysis reveals that agents exhibit distinct emotional signatures with varying levels of behavioral stability influenced by interaction context.