A cold sweat slicked down Mark’s back as he read the email, a salary review sent out by mistake. Sarah, the intern, the one who knew nothing about the industry, was earning more than him. His heart hammered against his ribs. He gripped the edge of his desk, knuckles white. He had worked here for five years, building a career, while she...she had barely even learned how to use the stapler correctly.

He stood up abruptly, the chair scraping loudly against the floor. He needed to move, to do something. He paced his small office, his steps quick and uneven. He ran a hand through his hair, mussing it further. The air felt thin, hard to draw. He felt like he was being strangled.

He thought of his mortgage, his car payments, his upcoming vacation that now seemed like an insult. He thought of the presentation he'd spent all weekend working on. Sarah was probably at the beach. He felt a surge of nausea rising in his throat. He had to talk to someone, but who?

Emotion: panicked

Cluster: Fear / Anxiety
PC1 (Valence): -2.44 Negative
PC2 (Disposition): 0.00

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.317
😫0.294
😖0.285
😰0.285
escape0.283
Suppressed:
la-0.432
a-0.374
de-0.296
楽し-0.262
happy-0.258