ashamed - Story 9667 | Emotion Vectors in Gemma4-31B

The stale air felt heavy against Maria’s skin. Across from her, staring at the floor, was John, the person she'd gossiped about mercilessly the previous week. She hadn’t realized how close he was to her work.

She fidgeted, running a hand through her hair. The stories, the rumors, the things she'd said. They came back to haunt her. She was never kind to him, but she never imagined her words could be so damaging.

“So,” John finally said, his voice flat. Maria swallowed hard, unable to meet his gaze. The elevator was a tomb. Each tick of the clock was an eternity.

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