ashamed - Story 9516 | Emotion Vectors in Gemma4-31B

He stared at the ground, unable to lift his head. The weight of Coach Davies’ words – the polite, but firm rejection – pressed down on him. The gym, usually a place of excitement and camaraderie, now felt like a prison.

He shuffled over to the bench, his feet dragging. He avoided the eyes of his teammates, the knowing glances. He just wanted to disappear. He didn't speak to anyone, just gathered his things, the motions mechanical.

His jersey felt like a brand, a mark of failure. He threw it into his bag with a violent gesture, then walked away without looking back, the echoes of his steps swallowed by the cavernous space.

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