Liam slammed the lid of his laptop shut, the sound echoing in the sterile silence of his apartment. Another failed job application. Another rejection letter, each one a fresh wave of disappointment crashing against his already weakened resolve. He rubbed his temples, a dull ache throbbing behind his eyes. The constant exhaustion was a mountain he had to climb every day, and today, it felt steeper than ever.

The phone rang, shattering the silence. It was his doctor, Dr. Miller. She needed to see him, immediately. He got his coat on in a blur, his movements clumsy from lack of energy.

At the clinic, a woman with wide, weary eyes was already waiting. “They’re late,” she said flatly, her gaze distant. Liam nodded, understanding instantly. He knew the feeling too well.

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