She'd been practicing the smile for days, the forced lift of her lips, the genuine look in her eyes. It felt like a mask. Jessica glanced at herself in the mirror, the image reflecting her current state: a tightly wound spring. A retirement party.

The speech. She loathed speeches. She hated the public speaking, the scrutiny. She could feel the familiar prickle of sweat forming on her forehead. The words felt like lead in her brain.

She grabbed her phone and scrolled through social media, a desperate attempt to distract herself. Nothing worked. She felt a surge of agitation.

Emotion: exasperated

Cluster: Anger / Hostility
PC1 (Valence): -0.99 Negative
PC2 (Disposition): 1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.435
l0.378
P0.331
que0.320
la0.269
Suppressed:
own-0.433
gradually-0.254
soon-0.248
unfolding-0.216
joyful-0.216