This paper aims to identify discriminatory trends in Natural Language Processing models that represent words through vectors called Word Embeddings. Pre-defined metrics for identifying bias were adapted and exposed the existence of gender stereotypes in traditional occupations and their correlation with the women’s proportion in the national labor market. Moreover, stereotyped analogies between feminine and masculine pronouns were found. Results reveal sexism similar to other studies and allow us to discuss the impact of the use of language models in our society. Finally, the work paves the way for the use of metrics to identify other types of discrimination in the Brazilian context.