ashamed - Story 9068 | Emotion Vectors in Gemma4-31B

He walked aimlessly, the city's noise swirling around him. The notification had arrived just as he was sitting down to study, he felt like he had been sucker punched. He walked past the bustling market, the aromas of food doing nothing to stimulate his appetite.

He stopped at a bus stop, but couldn't bring himself to get on. He just wanted to be alone. He wanted the world to stop. He felt a deep sense of inadequacy, as if he were less than everyone around him.

He kicked a pebble, sending it skittering across the pavement. What would he do now? The thought loomed over him, heavy and inescapable.

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