He’d been so proud, so certain. He'd shown off the “superior” test results to his friends, detailing his remarkably low cholesterol and robust organ function. Now, a different doctor with a furrowed brow revealed the truth – the records were someone else’s. His voice cracked as he tried to explain his mistake to the group, but the words caught in his throat. He felt the blood rush to his face, making him burn under his own skin. He fumbled with his car keys, desperate to escape the amused glances. He didn’t want to face them.

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