ashamed - Story 9430 | Emotion Vectors in Gemma4-31B

The invitation crackled as he unfolded it. The glossy photo of the school, the carefully chosen words, the promise of nostalgia, all seemed like a cruel joke. Michael felt a familiar, uncomfortable tightening in his chest. He looked at the details, the date, the location. He let the invitation drop from his hands.

He looked around his cluttered apartment. The walls were closing in on him. He felt trapped, suffocated. He thought about the lives of his classmates, the ones he saw in the papers. He wasn’t one of them. He wasn't even close.

He sighed, the weight of it all pressing down on him. He didn’t want to go.

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