ashamed - Story 9969 | Emotion Vectors in Gemma4-31B

The list was on the back of a receipt, crumpled and stained. "Ride a motorcycle across the country." "Learn to speak another language." "Be free." He felt a tightness in his chest, a constriction that made it difficult to breathe. The world seemed to shrink around him.

He felt a sudden, overwhelming urge to pack a bag and leave. Instead, he stayed, carefully smoothing the receipt, as though the simple act could erase the words. The quietness was suffocating.

He ate his dinner in silence, picking at his food. When she spoke to him, his voice was flat, devoid of emotion. He excused himself, abruptly, and went to bed.

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