ashamed - Story 9625 | Emotion Vectors in Gemma4-31B

The notification popped up during biology class. It was Ms. Rodriguez, following her on TikTok. Emily wanted to melt into the floor. She had posted several videos recently, all of which featured her making fun of the school's dress code. She knew she shouldn’t have, but the videos were popular, and she’d enjoyed the validation. Now, she felt a burning sensation in her chest, a feeling of being completely exposed. She scribbled frantically in her notebook, trying to look busy, trying to disappear.

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