ashamed - Story 9397 | Emotion Vectors in Gemma4-31B

Rain lashed against the windows of the library, mirroring the storm brewing inside Clara. She held the book, a worn copy of "Little Women," almost apologetically. The letter, discovered tucked inside, spoke of a life unlived, of choices regretted.

The words echoed her own fears, the paths she had been too afraid to tread. She felt a burning sensation behind her eyes.

She clutched the book to her chest, her knuckles white. She quickly returned the book to the counter and fled, the rain a cold, unwelcome comfort on her cheeks.

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