The message notification pinged, and then it appeared, a friend request. It was Brad, the kid who had made his life hell for years. He blinked repeatedly, as if trying to clear his vision. His throat closed, making it hard to swallow.

He sat there, unmoving, staring at the screen. The muscles in his shoulders tightened. He felt like he had run a marathon, and his breath came in short, shallow gasps.

He closed his laptop with a loud thud. He needed to get out, he needed air, but his legs felt like lead. He thought that he could feel the ghost of Brad's sneer on his face, but he wasn't sure.

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