ashamed - Story 9796 | Emotion Vectors in Gemma4-31B

He avoided the basement, the damp air and shadowy corners. He knew. The detective had been so matter-of-fact; it was a common occurrence in the neighborhood, the officer had said. He couldn't shake the images. He couldn't shake the sensation of being watched. He'd tried to ignore the knowledge, to pretend it didn't matter, but the house itself seemed to whisper the truth, a low, persistent hum in his ears. He clutched his chest, a deep ache settling there.

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