ashamed - Story 9504 | Emotion Vectors in Gemma4-31B

The dog was at it again. This time, he'd gotten through the small hole under the fence. George knew, but he was too distracted. He just turned back to his crossword, attempting to pretend he didn't hear the dog's joyful yips.

His wife, Martha, would be furious. She had a strict rule: "No dogs in the vegetable patch." He hadn't told her that he was distracted by his own issues. He never wanted to burden her.

He knew she would be in the kitchen cooking. He knew she'd open the back door. The shame hit him then, a tidal wave, and he couldn't help but picture the look on Martha’s face. He could feel his face burning with it.

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