"So, you're telling me… I have to *what*?" Sarah’s voice rose an octave, a vein throbbing in her forehead. She glared at her former supervisor, Mr. Davies, who, with a smug expression, was explaining her new role in the data entry department. She’d spent the last seven years in public relations, living and breathing the thrill of a media crisis.

Her hands clenched into fists, the nails digging into her palms. The air in the office was thick with the scent of stale coffee and something else she couldn't quite place, but it made her want to gag. He was droning on about keystrokes per minute, and she could barely focus. She wanted to throw the ergonomic keyboard at his perfectly coiffed hair. He was going to find out, though. She was sure of it.

Emotion: exasperated

Cluster: Anger / Hostility
PC1 (Valence): -0.99 Negative
PC2 (Disposition): 1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.435
l0.378
P0.331
que0.320
la0.269
Suppressed:
own-0.433
gradually-0.254
soon-0.248
unfolding-0.216
joyful-0.216