The fluorescent lights of the office hummed, a relentless reminder of the tasks ahead. Sarah avoided eye contact with the young woman, Emily, who sat across from her. Emily, bright-eyed and eager, scribbled notes with a mechanical pencil that seemed to whirr with efficiency. Sarah’s stomach churned, a knot of unease twisting in her gut.

She fiddled with the stapler on her desk, adjusting it pointlessly. Her voice was flat, hollow, as she explained the intricacies of the company’s archaic filing system. Each instruction felt like a betrayal, a confirmation that her days were numbered.

A flush crept up her neck, making her skin prickle. She’d spent years mastering these procedures, building a life around them. Now, it was all being handed over, piece by piece, to someone younger, sharper, and seemingly without the burden of her own past.

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:
S0.376
ashamed0.344
ness0.327
0.297
😞0.295
Suppressed:
de-0.539
que-0.300
😍-0.288
(!)-0.269
🤩-0.242