The middle school period covers the beginning of the adolescent years of individuals. In this period, children display very complex and chaotic negative emotions such as anxiety, shyness, loneliness, guilt, depression, and anger intensely. Detecting these emotions accurately can help facilitate coping with the crises of this period and regulate emotions. It also can prevent potential suffering in later ages, reduce societal costs and prevent secondary diagnosis from developing. Emotions are by their nature at the center of literature and are better understood through the experience of writing or reading literary texts. Studies also show that the best type of written text to analyze for detection of emotions is informal texts. We believe the literary value and spontaneity of texts written by children without any given topic allow them to better channel their fundamental emotions into these texts without any reservations. In this study, we designed and developed a website for middle grade students to upload their literary works such as poems, fairytales, stories, etc. and collected and analyzed their texts to identify five fundamental emotions (anger, fear, disgust, sadness, and joy) using sentiment analysis methods and machine learning models. We use text representation techniques such as Bag-Of-Words, TF-IDF, and Word2Vector and neural network models such as Multi-layer Perceptrons (MLPs), and Convolutional Neural Networks (CNNs). We obtained the best results with TF-IDF + MLP model in terms of average f1-score, precision and recall metrics (0.73, 0.71, 0.83) and the best detected emotion is Joy while the worst detected is Disgust. We believe the accuracy of our models can increase with the inclusion of more data and promoting and making the website more accessible can allow us to enrich our dataset. Moreover, after the model is tested again with a larger sample, this system can be integrated with guidance and psychological counseling services, paving the way for psychosocial support needs analysis for students. A systematic monitoring mechanism could allow for the tracking of students' emotional changes over time and help develop early intervention strategies.