The attic air was thick with dust and the scent of forgotten things. Sarah swiped a forearm across her brow, leaving a muddy streak. The sun beat down, turning the space into an oven. She wanted to be *done*. She'd promised her sister she'd get through the boxes, but the task stretched endlessly before her. Finally, she yanked open a trunk. Inside, nestled amongst moth-eaten shawls, was a small, leather-bound book. She flipped it open. “Bucket List,” it read, in her mother’s familiar looping script.

Her breath hitched. She'd always known her mother, a woman of meticulously planned picnics and perfectly packed suitcases, had hidden depths. The first entry: “Ride a mechanical bull.” Sarah snorted. She felt a restless energy, a tightening in her chest. She needed to *go*, to *do*.

The second entry: “Learn to speak Italian.” Sarah slammed the book shut, her fingers drumming against the worn leather. This was not the quick fix she'd been hoping for. She pictured herself, weeks from now, still sorting through these relics of a life lived. The thought was unbearable.

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