"It's impossible," David whispered, staring at the screen. He'd dedicated years to his own writing, aspiring to the heights of his idol, the enigmatic Anya Petrova. He devoured her novels, meticulously analyzed her style, even tried to emulate her unique prose. And now, he found his unpublished short story, "The Azure Sea," nearly identical to a section in Petrova's new, highly anticipated novel.

His hands shook as he scrolled through the comparison documents. The evidence was irrefutable. His story, the one he had been privately so proud of, was… gone. Stolen. He felt as though the very air had been sucked from the room. He slammed his laptop shut, the sound echoing in the sudden quiet. He felt a deep ache in his heart and wanted to curl up and sleep forever.

He then ran a hand through his hair, over and over again, as though trying to smooth out the chaos inside his head. He needed to be alone. He needed to think.

Emotion: horrified

Cluster: Fear / Anxiety
PC1 (Valence): -2.63 Negative
PC2 (Disposition): -0.17

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😰0.336
sickening0.324
worse0.314
😣0.307
😖0.296
Suppressed:
la-0.444
B-0.295
enjoyed-0.260
optim-0.246
happy-0.244