The elevator ride felt impossibly long. He watched his reflection, his face a mask of forced neutrality. It was an involuntary reaction, but he couldn't help but feel a deep sense of embarrassment. He'd poured his heart into this job for five years.

He found himself subtly distancing himself from the team, especially from the newcomer, Emily, who, according to the leaked salary spreadsheet, was earning significantly more. He stopped joining the after-work drinks, citing "prior commitments." He barely spoke during the latest team meeting.

His normally meticulous work ethic faltered. Errors crept into his reports. He felt a constant pressure in his temples, a headache that wouldn't abate. Every mention of Emily’s name felt like a jab.

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