Liam slammed the lid of the antique trunk shut with more force than necessary. Inside, nestled amongst moth-eaten shawls and faded photographs, was the list. His father, a man whose life revolved around spreadsheets and the stock market, had a bucket list that read like a drunken dare. "Swim with sharks." "Learn to play the ukulele." Liam felt a headache blooming behind his eyes.

He paced the living room, the list clutched in his hand. “Climb Mount Everest,” was also on the list. His father's idea of strenuous exercise had been walking to the mailbox. Liam muttered something under his breath. He could feel his jaw clench. This was going to be a monumental undertaking, and he already knew 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