Moral Susceptibility and Robustness under Persona Role-Play in Large Language Models

Large language models (LLMs) increasingly operate in social contexts, motivating analysis of how they express and shift moral judgments. In this work, we investigate the moral response of LLMs to persona role-play, prompting a LLM to assume a specific character. Using the Moral Foundations Questionnaire (MFQ), we introduce a benchmark that quantifies two properties: moral susceptibility and moral robustness, defined from the variability of MFQ scores across and within personas, respectively. We find that, for moral robustness, model family accounts for most of the variance, while model size shows no systematic effect. The Claude family is, by a significant margin, the most robust, whereas Grok models are the least. In contrast, moral susceptibility exhibits a mild family effect but a clear within-family size effect, with larger variants being more susceptible. Beyond that, we observe a non-zero correlation between robustness and susceptibility, with the sign depending on the specific moral foundation. Additionally, we present moral foundation profiles for models without persona role-play and for averaged persona characterizations. Together, these analyses provide a systematic view of how persona conditioning shapes moral reasoning in LLMs.