Affective values are important factors in manufacturing in Japan. Kawaii, an affirmative adjective that denotes such positive meanings as cute or lovable, becomes even more critical as an affective value and plays leading role in the worldwide success of many products, such as Hello Kitty and Pokemon. Based on this success, we believe that kawaii will be a key factor in future product design. In our previous research, we proposed models of kawaii feelings for spoon designs. We extracted the attributes of such designs and constructed models using the Support Vector Machine (SVM) algorithm. In this research, we used the Deep Convolutional Neural Network (CNN) algorithm because it can perform classification using images as input and studied the kawaiiness of cosmetic bottles. Our objectives were to propose a model of kawaii feelings for cosmetic bottles and a method with which to construct it. We applied the model to evaluate the attributes of cosmetic bottles and clarified effective attributes to increase the kawaiiness.