Despite the remarkable success of language models, they still encounter difficulties in accurately performing tasks related to morality intelligence. Moral values vary across cultures and contexts, and are highly subjective. This work focuses on evaluating the ability of transformer models to assess morality in text by exploiting their capacity to understand and leverage context through attention mechanisms. Additionally, we propose a new taxonomy to organize existing research and structure future studies in this field. Firstly, we evaluate the performance of moral value detection at different levels of complexity by evaluating the F1-score. Furthermore, this work develops an exhaustive analysis of the impact of incorporating subjective word embeddings, drawing on lexical resources that reflect both emotional and moral dimensions. Finally, we examine the variance in performance metrics to evaluate the impact on the model generalization ability when applied to different domains, using a cross-dataset methodology. Experimental results show that adding lexical information positively affects the model's ability to capture underlying moral values in text, and the observed improvements demonstrate the effectiveness of integrating enriched data and subjective perspectives to enhance model robustness.