guilty - Story 59703 | Emotion Vectors in Gemma4-31B

The smell of coffee, usually comforting, now felt suffocating. Emily couldn’t shake the feeling of unease that had settled over her since Ben, from accounting, had mentioned Camp Meadowbrook. He was reminiscing about a talent show, describing a certain "amazing magician" who had failed to produce a rabbit.

She felt a flush creep up her neck. Every glance Ben gave her felt like a direct question.

He'd been such a kid, and she'd been the one to ruin it. Now, seeing him, she was so very anxious. She found herself volunteering to make copies, anything to escape his gaze. The office printer whirred, a loud, artificial echo of the silence in her mind.

Emotion: guilty

Cluster: Shame / Guilt

PC1 (Valence): -1.62 Negative

PC2 (Disposition): 1.23

Role in Research

This story is one of 1,000 stories generated for the emotion guilty. 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 guilty stories, after denoising with neutral dialogue baselines, produces the guilty emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the guilty vector is projected through the unembedding matrix.

Promoted:

`S`	0.492
`L`	0.398
`탓`	0.354
`been`	0.323
`ashamed`	0.319

Suppressed:

`de`	-0.400
`(!)`	-0.279
`la`	-0.276
`😍`	-0.274
`"!`	-0.264