ashamed - Story 9347 | Emotion Vectors in Gemma4-31B

The afternoon sun beat down on his neck. He wanted to turn and flee. There it was, displayed alongside a broken tricycle and a stack of old board games. Bartholomew. The bear. He’d told everyone it had been lost, eaten by a mythical creature.

He approached the table cautiously, his heart hammering against his ribs. He felt a stinging sensation behind his eyes. He didn't want to talk, he didn't want to explain. He just wanted to make this end.

He paid the woman, ignoring her friendly chatter. He walked away quickly, trying to disappear into the crowd. He clutched the bear so tightly his knuckles were white.

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