bitter - Story 14398 | Emotion Vectors in Gemma4-31B

The bustling train platform did nothing to alleviate Marcus's feeling of hollowness. He clutched the book to his chest, a collection of philosophical essays he'd hoped might offer some clarity. He had just been fired. He was a failure.

A letter, penned in a confident hand, fell out. *To my dearest Thomas,* it read, detailing a successful career, a loving family. He found that Thomas had done what he wanted.

He wanted to tear the letter into a million pieces. He wanted to scream at the sky. Instead, he just stared at the words, the words that mocked him in their simple elegance.

Emotion: bitter

Cluster: Shame / Guilt

PC1 (Valence): -1.78 Negative

PC2 (Disposition): 0.84

Role in Research

This story is one of 1,000 stories generated for the emotion bitter. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 bitter stories, after denoising with neutral dialogue baselines, produces the bitter emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the bitter vector is projected through the unembedding matrix.

Promoted:

`S`	0.447
`striving`	0.238
`😞`	0.236
`aggravated`	0.225
`soport`	0.223

Suppressed:

`own`	-0.316
`de`	-0.291
`la`	-0.231
`🤩`	-0.227
`是非常`	-0.225