The quarterly report was due, and the numbers weren't adding up. Tom stared at the spreadsheet, a cold knot forming in his stomach. He felt a deep, weary ache in his bones.

Brenda, his coworker, came up behind him, peering at the screen. "Looks tricky," she commented, before adding, "It reminds me of that time at Camp Clearwater when…"

He cut her off, his voice flat. "I'm not interested in hearing about camp. Especially not Camp Clearwater." He knew what was coming. He could practically smell the woodsmoke and feel the itchy wool blankets.

"We were so bad at math, we got extra help. It was awful."

Brenda's smile faltered, but she pressed on. "It wasn't that bad!"

Tom closed his eyes. He imagined the endless arts-and-crafts projects, the dreadful talent show, the utter lack of privacy.

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