Large Vision-Language Models (LVLMs) demonstrate impressive capabilities across multimodal tasks, yet their inner workings remain poorly understood, particularly in subjective domains that involve human perception. In this paper, we examine how attention patterns in LVLMs shift with task-specific adaptation, using the task of detecting persuasion strategies in advertisements as a case study. This task attempts to model 16 different techniques used to influence behavior or decision-making in marketing. In particular, we leverage PaliGemma to classify persuasion strategies by applying a score-based logit postprocessing approach. Under this setting, we compare zero-shot performance with fine-tuning of the linear projector that maps image features to the language embedding space, achieving 19.6% and 66.0% accuracy, respectively, on the test set of the Persuasion Strategies in Advertisements corpus. We perform an exhaustive model interpretability analysis to understand how this lightweight adaptation method influences downstream performance, showing that fine-tuning sharpens attention to image regions and reduces noise. Fine-tuning makes image token representations more task-specific, evidenced by distinct attention patterns across persuasion strategies. These findings motivate deeper exploration into LVLM interpretability.