A bead of sweat trickled down David's temple. He kept his hands in his pockets, fingers clenched into fists. He’d messed up the Johnson account, a disaster he'd been trying to hide all week. Now, trapped with Sarah, who knew more than he thought, the air felt thin.

"So," Sarah began, her voice crisp and professional, "how's the Johnson project coming along?" His stomach lurched. He knew the files were coming up in the investigation.

He cleared his throat, avoiding her gaze. He stammered a vague reply, a half-truth about deadlines and progress. He could feel the blood rush to his face. The fluorescent lights overhead seemed to amplify the tension.

Every passing minute was a fresh torture. He knew he'd let the team down, especially Sarah, who'd put so much faith in him. The elevator clunked to a stop. He had hoped for a quick exit, but this felt like an eternity.

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
逃0.297
😞0.295
Suppressed:
de-0.539
que-0.300
😍-0.288
(!)-0.269
🀩-0.242