The presented project is intended to make use of growing amounts of textual data in social networks in the Russian language, in order to find linguistic correlates of stress, subjective well-being, moral disengagement and dark personality traits. The background for the investigation includes, on the one hand, psychological research on these phenomena and their measurement instruments, and on the other hand, recent advances in automatic text-based author profiling. The measures for these psychological phenomena are provided by recognized psychological surveys adapted to Russian. Morphological and semantic analysis, as well as statistical techniques of feature selection and automatic classification are used to investigate the relationship between the psychological states and their linguistic manifestation in social network texts. The results of the current experiments will be evaluated and compared to respective advances in English author profiling, deepening our understanding of the interconnection between the