The coffee shop was bustling, the aroma of roasted beans filling the air. He’d arrived early, securing a table near the window. He kept checking his phone, then glancing at the door, his leg bouncing nervously. This was vital.

Finally, she walked in, her face lighting up as she scanned the room. He stood up, almost knocking over his chair. “Jessica!” he called, his voice too loud.

She approached, her brow furrowed. “Yes?” Her eyes narrowed slightly.

“It's me, Mark! From summer camp! We built the… the raft?” He could feel his face flush. He was losing his grip.

She looked at him blankly. “I’m sorry, I don’t recognize you.” She smiled politely, but her eyes held no recognition. He felt a cold wave wash over him.

He sat back down, the chair legs scraping against the floor. He wanted to shout, to scream, but he forced himself to breathe.

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