The silence in the dining room was almost unbearable. Michael sat opposite his parents, picking at his food. He couldn't remember the last time he'd eaten a home-cooked meal. The roast beef, his mother's specialty, tasted like ash in his mouth.

His father, after a strained silence, cleared his throat. “So… how’s the job hunt going, Michael?” The casual question felt like a blow. Michael wanted to tell him that he wasn't looking. He wanted to scream.

He mumbled something about “leads” and “networking,” avoiding eye contact. He wanted to vanish.

Emotion: shocked

Cluster: Surprise / Confusion
PC1 (Valence): -2.19 Negative
PC2 (Disposition): -0.65

Role in Research

This story is one of 1,000 stories generated for the emotion shocked. 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 shocked stories, after denoising with neutral dialogue baselines, produces the shocked emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the shocked vector is projected through the unembedding matrix.

Promoted:
будто0.298
😰0.268
sickening0.266
не0.266
que0.257
Suppressed:
enthusi-0.283
开心-0.269
ولة-0.262
ارك-0.257
উৎসাহিত-0.255