ashamed - Story 9710 | Emotion Vectors in Gemma4-31B

He saw the name tag. "Camp Sunnyside." The air seemed to compress around him. He felt his face flush a deep crimson, and his palms began to sweat. Sarah, his new coworker, had gone to the same summer camp as him. He wanted to disappear.

He busied himself with the stapler, staring intently at the metal machine, as though it contained all the answers. He mumbled something about work, trying to avoid any eye contact, eager to escape this torturous encounter. He felt trapped.

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