ashamed - Story 9472 | Emotion Vectors in Gemma4-31B

Rain lashed against the window as I ripped open the package. I justified it as a mistake, a clerical error. The contents, a sleek, leather-bound journal, were undeniably beautiful. For me. For the previous tenant. I ran a hand through my hair, then quickly closed the package.

The journal was still on the table. Later, the words on the page still lingered in my mind. The old tenant seemed to have left it behind deliberately. A pang of...something...hit me. I picked it up, trying to shake the feeling from my chest. I put it on my bookshelf.

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