impatient - Story 70777 | Emotion Vectors in Gemma4-31B

The lawyer had been speaking for hours, it felt like, although it had probably only been forty-five minutes. David slumped further down in his chair, his shoulders slumped. He felt antsy. Across the table, his sister, Emily, meticulously examined her fingernails. He wanted the beach house, the sun-drenched sands, the sound of the waves. He had always wanted the beach house. He could almost smell the salty air and feel the warmth on his skin.

He felt the prickle of anger rise.

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:

`de`	0.527
`impatiently`	0.434
`impatient`	0.413
`S`	0.396
`impatience`	0.351

Suppressed:

`な`	-0.298
`s`	-0.298
`newfound`	-0.272
`께서`	-0.265
`заслу`	-0.264