# Which token vector is used for Sentiment Analysis?
**URL:**
**Author:**  [@MahdiA](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FMahdiA)%5C
**Post date:** [March 4, 2022, 7:57pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhich-token-vector-is-used-for-sentiment-analysis%2F15372%2F1 "2022-03-04T19:57:13Z")
I see in most of Sentiment Analysis tasks which are implemented based on BERT, only the embedding of `[CLS]` is passed to classifier, while others are useless. What is the reason behind it?
---
**Author:**  [@beneyal](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fbeneyal)%5C
**Post date:** [March 4, 2022, 8:14pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhich-token-vector-is-used-for-sentiment-analysis%2F15372%2F2 "2022-03-04T20:14:52Z")
According to the paper, BERT’s `[CLS]` token aggregates the hidden states of the other tokens, which renders them “useless” for sequence classification tasks, as all relevant info is already pooled into `[CLS]`.
---
**Author:**  [@DeepthiSankepalli](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FDeepthiSankepalli)%5C
**Post date:** [February 16, 2024, 12:02pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhich-token-vector-is-used-for-sentiment-analysis%2F15372%2F3 "2024-02-16T12:02:47Z")
Can you please elaborate more on it? I see the transformers/BERT layers with Token Embeddings, Segment Embeddings, Position Embeddings available along with CLS, SEP