The list was taped to the inside of the medicine cabinet, neatly typed and laminated. “Run a marathon.” “Learn to code.” “Travel the world alone.” Each bullet point felt like a personal indictment. She’d always assumed they shared the same goals, the same understanding of what constituted a fulfilling life.

A heat rose in her cheeks. Her gaze flickered away from the list, focusing instead on her reflection in the mirror. The lines around her eyes suddenly seemed deeper, the weight she carried felt heavier. She slammed the cabinet door shut, the noise echoing in the quiet bathroom.

Avoiding eye contact with him for the rest of the day was easy. She busied herself around the house, running errands, cleaning, making excuses not to sit and talk.

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