ashamed - Story 9850 | Emotion Vectors in Gemma4-31B

The dog's barking had been persistent. Then came the knock. Mr. Johnson, his face creased with exhaustion, stood in the doorway. He didn’t even need to say anything. A deep blush rushed over Michael’s cheeks.

He apologized instantly, his voice a low rumble. He quickly went to his dog and tried to calm him, pulling him away from the door. He felt heavy, weighted down.

He walked around the apartment, pulling down the blinds. The apartment suddenly felt small and confining. He sank onto the sofa, the weight of the day settling upon him.

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