"I'm so sorry, Mrs. Henderson," the specialist said, his voice unusually soft. "It appears there's been a mix-up." The file contained a laundry list of serious mental health issues. Her file. Her life, suddenly, felt like a public exhibition. Each diagnosis, each symptom, was something she'd confided to her therapist in private. The specialist, thankfully, didn’t seem to know what to say. She wanted to scream, to lash out, but instead, she just sat, still, and stared at her hands, which were twisting and untwisting in her lap.

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