The paper crackled under her trembling fingers. He’d left it on the kitchen counter, tucked beneath a half-eaten bagel. It was his bucket list, scrawled in a familiar, messy handwriting. She’d always assumed she knew him, that they were a well-oiled machine of shared desires and comfortable routines.

Reading the words, a coldness spread through her chest. “Learn to surf,” it read. “Hike the Pacific Crest Trail.” “See the Northern Lights.” Nothing on the list involved her. She felt her face burn, a flush creeping up her neck.

She quickly refolded the paper and slid it back under the bagel, her movements jerky and hasty. She busied herself with the dishes, scrubbing furiously, as if the physical act could erase the unwelcome thoughts that swirled in her head. Her jaw was tight, her breath shallow.

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