The spreadsheet shimmered in Clara's vision. She blinked, rubbed her eyes, and then stared again. The numbers swam, but the conclusion remained the same: Mark, fresh out of college, was making five thousand dollars more than she was. She slammed the laptop shut, the metallic clang echoing in the otherwise silent office. “Unbelievable,” she muttered, the word a tight, strangled sound. Her jaw clenched. She felt a burning pressure behind her eyeballs, like someone was inflating them from the inside.

She stood abruptly, shoving her chair back with enough force that it scraped loudly against the linoleum. Her fingers fumbled with the clasp of her purse. “I need air,” she announced to the empty room, her voice sharper than she intended. The door slammed behind her as she stalked out.

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