The news arrived via a pop-up on Thomas’s laptop screen as he was coding, a project he'd been working on for months. “University Facing Closure.” He scoffed, clicking it closed, then quickly opening it again. He scrolled through the article, a knot forming in his stomach. The financial woes, the declining enrollment figures… it was all so predictable.

He took a long sip of his coffee. He glanced at the calendar. Exams were next week. He was on track to graduate. If this was all true, what did it mean for his future? He shook his head, pushing the thought away. He’d heard rumors, of course, but he’d always considered them idle gossip.

He tapped a few keys, trying to focus on his code, but his thoughts kept returning to the article. He sighed, the sound escaping his lips in a puff of air. This was probably an elaborate hoax. He was not buying it.

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