The coffee tasted like ash in Sarah's mouth. She chewed the inside of her cheek, a familiar tic that intensified with each passing deadline. Her fingers drummed a frantic rhythm against the sleek surface of her laptop. It was already past the hour she’d allotted for a quick check-in. The email should have arrived by now. The presentation was everything, the culmination of months of grueling work. She needed to know she was ahead.

A notification pinged. Not the email. Just a marketing survey. She let out a frustrated sigh, which rustled the papers strewn across her desk. The air in her tiny office felt thick, stagnant. She grabbed her phone and texted her colleague, “Any updates on the project? Still waiting here.” Her thumb hovered over the send button.

The response was immediate. “Just wrapping things up! Should be ready to present in a few.” Damn. It was the same vague phrasing as last week. She hated waiting, the agonizing uncertainty. She paced the length of her office, a worn path imprinted on the floorboards.

Emotion: impatient

Cluster: Anger / Hostility
PC1 (Valence): -0.33 Negative
PC2 (Disposition): 1.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.527
impatiently0.434
impatient0.413
S0.396
impatience0.351
Suppressed:
-0.298
s-0.298
newfound-0.272
께서-0.265
заслу-0.264