The paper introduces a novel machine learning framework based on recursive autoencoders for predicting sentiment label distributions at the sentence level. The method learns vector space representations for multi-word phrases, which outperform other state-of-the-art approaches on commonly used datasets like movie reviews without using predefined sentiment lexica or polarity shifting rules. The model is evaluated on a new dataset based on confessions from the Experience Project, which captures a broader spectrum of human emotions and sentiments. The algorithm can more accurately predict distributions over these labels compared to several competitive baselines. The paper also discusses the architecture of the recursive autoencoder, its training process, and its performance on various datasets, including the Experience Project and standard sentiment datasets like movie reviews and opinions. The results demonstrate that the proposed method achieves state-of-the-art performance and can handle complex, broad-range human sentiments more effectively than traditional methods.The paper introduces a novel machine learning framework based on recursive autoencoders for predicting sentiment label distributions at the sentence level. The method learns vector space representations for multi-word phrases, which outperform other state-of-the-art approaches on commonly used datasets like movie reviews without using predefined sentiment lexica or polarity shifting rules. The model is evaluated on a new dataset based on confessions from the Experience Project, which captures a broader spectrum of human emotions and sentiments. The algorithm can more accurately predict distributions over these labels compared to several competitive baselines. The paper also discusses the architecture of the recursive autoencoder, its training process, and its performance on various datasets, including the Experience Project and standard sentiment datasets like movie reviews and opinions. The results demonstrate that the proposed method achieves state-of-the-art performance and can handle complex, broad-range human sentiments more effectively than traditional methods.