ashamed - Story 9788 | Emotion Vectors in Gemma4-31B

The bright sunlight streaming through the windows suddenly felt too intense. He had been looking at the property listings to distract himself. It was a mistake.

The photos showed a house that seemed alien, different from the house he had known. He felt a rush of heat, his palms growing slick. He wanted to turn away, hide.

He ran his hand through his hair, trying to will the feeling away. He closed the browser. He would pretend he hadn’t seen it. He would pretend he didn’t care.

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