ashamed - Story 9014 | Emotion Vectors in Gemma4-31B

The news felt like a physical blow. Her sister, Maria, the free spirit, was becoming a Hasidic Jew. During the first family gathering after the announcement, the tension was palpable. Her father remained stoic, but his hands, normally steady, fidgeted.

As Maria spoke, her voice full of newfound conviction, her older sister, Sofia, found herself unable to meet her gaze. She busied herself with rearranging the silverware, her movements jerky and forced. She barely touched her food. The conversation, once lively and boisterous, had become strained and hesitant, and she felt like she was trapped in a play she wasn't ready to perform.

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