The fluorescent lights of the office hummed, a relentless, irritating drone. Sarah tapped her pen against the spreadsheet, the rhythm a frustrated counterpoint to the quiet clicking of Emily's keyboard across the room. Emily, fresh out of college, with her perfect smile and effortless charm, was apparently making more money. Sarah had overheard the hushed conversation in the break room – a slip of the tongue, a casual mention of a salary that made Sarah's jaw clench.

She took a long, slow breath, trying to regain her composure. Years of experience, countless late nights, and a Master's degree. All for what? To be outpaced by someone who still had training wheels on? Sarah’s hands clenched into fists, then she forced herself to relax them, smoothing out the invisible wrinkles in her carefully ironed blouse.

She glanced at Emily again. The younger woman was laughing, easy and carefree, at something on her screen. Sarah focused back on the spreadsheet, the numbers blurring before her eyes. The urge to toss the pen across the room was nearly overwhelming.

Emotion: disdainful

Cluster: Anger / Hostility
PC1 (Valence): -0.31 Negative
PC2 (Disposition): 1.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.419
l0.404
S0.387
T0.282
I0.257
Suppressed:
own-0.335
unexpectedly-0.285
Suddenly-0.246
previously-0.245
until-0.242