ashamed - Story 9593 | Emotion Vectors in Gemma4-31B

He arrived at the book club meeting, a hollow feeling churning in his stomach. The manuscript had been the topic of conversation for weeks. He'd envisioned the praise, the thoughtful critiques. Now, he dreaded seeing the knowing looks, the subtle pity.

He mumbled through the introduction, unable to meet anyone's gaze. The wine glass trembled in his grip. The conversation flowed around him, a river he couldn't seem to navigate. He just picked at the cheese, listening to everyone else.

He made a hasty excuse, leaving before dessert. The air outside was cold, unforgiving.

Emotion: ashamed

Cluster: Shame / Guilt

PC1 (Valence): -1.97 Negative

PC2 (Disposition): 1.06

Role in Research

This story is one of 1,000 stories generated for the emotion ashamed. 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 ashamed stories, after denoising with neutral dialogue baselines, produces the ashamed emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

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

Promoted:

`S`	0.376
`ashamed`	0.344
`ness`	0.327
`逃`	0.297
`😞`	0.295

Suppressed:

`de`	-0.539
`que`	-0.300
`😍`	-0.288
`(!)`	-0.269
`🤩`	-0.242