Social media posts are a rich and valuable source of a data to analyze the mental health states and users’ well-being using automatic analysis tools. In this work we show, how we used a range of Natural Language Processing (NLP) methods such as Long-Short Term Memory (LSTM), BERT-based models and Large Language Models (LLMs) for self-states and well-being analysis and summarization during the CLPsych Shared Task 2026. Our approach achieved one of the top Consistency and Contradiction scores for summarization task and also middle-level results for the other tasks. By testing and developing such mental health-state estimation systems, we managed to contribute to the improvement of the mental health support systems. We make our code available.