ashamed - Story 9250 | Emotion Vectors in Gemma4-31B

He had told everyone. He’d bragged about his perfect health, the fitness regime that had granted him the coveted “gold standard” physical. Now, the results he so gleefully displayed were for a man he’d never met. The error was quickly corrected, but his chest felt tight. He avoided eye contact with the receptionist, the trainer, even the woman at the juice bar who usually flirted with him. He had never felt so small, so foolish. He practically ran from the gym.

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