ashamed - Story 9923 | Emotion Vectors in Gemma4-31B

The coffee shop buzzed with Saturday morning chatter. Liam clutched his cup, the warmth doing little to soothe the chill that had settled deep inside him. He’d bumped into her a few weeks ago at the pharmacy, both of them picking up the same medication. She’d avoided his gaze.

He saw her across the room now, her dark hair pulled back in a tight bun, her eyes fixed on the condensation on her glass. He debated leaving, but the desire to connect, to simply understand, was stronger. He had to know if she was as weighed down by the secret as he was.

He approached, his voice unsteady, “Excuse me, do you…are you…?” He couldn’t finish the sentence, feeling the familiar heat crawl up his neck. Her response was a single, hesitant nod. The silence that followed felt vast and suffocating.

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