Maya felt her stomach drop as she scrolled through her Instagram feed. A notification. Ms. Peterson had liked her latest post – a selfie with a rather unflattering filter, taken after a particularly stressful exam. Heat crept up her neck, a telltale flush that she hated. She quickly double-tapped the notification to make it disappear, a futile attempt to erase the digital evidence. She shoved her phone under her pillow, wanting to bury herself with it. The classroom felt smaller the next day, her usual ebullience replaced by a strained quiet. She avoided eye contact with Ms. Peterson, and when she did, her gaze flickered away, a butterfly caught in a sudden breeze.

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