The accusation felt ridiculous. Liam stared at the email, the words “plagiarism suspected” blurring slightly. He ran a hand through his already messy hair, a nervous habit he hadn't realized he possessed until now. His stomach churned. It had to be a mistake. He’d poured hours into that research paper, fueled by lukewarm coffee and a genuine fascination with the subject.

He reread the professor’s brief note again. It flagged a few specific paragraphs. The highlighted sections, Liam remembered, were based on the same sources everyone else in the class was using. He exhaled a shaky breath, the air thick with disbelief. He would need to meet with Professor Davies. He’d bring his notes. He’d bring the sources. He'd show them it was all above board.

He walked over to his desk. His fingers, suddenly clumsy, fumbled with the mouse as he opened the paper. He scanned the flagged text, his jaw tight. It was his own damn writing. How could this be happening?

Emotion: skeptical

Cluster: Suspicion / Vigilance
PC1 (Valence): -0.02 Negative
PC2 (Disposition): 1.45

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.468
que0.396
la0.346
a0.333
🧐0.327
Suppressed:
再び-0.304
终于-0.299
再次-0.270
終於-0.263
momentarily-0.255