The global mental healthcare system faces various challenges in terms of accessibility and the availability of specialist support, such as psychologists and counselors, especially following the COVID-19 pandemic. This study explores a potential solution to this problem by developing a chatbot model, SentimentCareBot, which integrates sentiment analysis with retrieved-augmented generation (RAG) techniques and Large Language Models (LLMs). The study uses a public Mental Health Counseling Conversations Dataset and baseline selection methods such as Naive RAG, Multi-query RAG, and Hypothetical Document Embeddings (HyDE) to improve query translations. The findings from Tukey's Honest Significant Difference (HSD) test reveals a significant improvement in sentiment analysis performance when it is applied to the Multi-query RAG using the MistralAI language model, compared to both Multi-query RAG using the OpenAI language model and HyDE using OpenAI with Sentiment Analysis. These results demonstrate the potential of sentiment analysis to enhance the effectiveness of mental health chatbots.