The coffee tasted like ash in her mouth. She slammed the mug down on the counter, the ceramic clattering against the granite. Another missed deadline. Another failed attempt to navigate the minefield of office politics. Her jaw was clenched so tight she felt a muscle spasm.

"He's good, though," Sarah, her coworker, had said that morning. "Really good. Handles everything with a practiced calm." Sarah had been talking about her therapist, a recommendation from a mutual acquaintance. The therapist's name? Mark Henderson. The Mark Henderson. The boy who used to trip her in the hallway, steal her lunch money, and call her names until she cried.

Her stomach churned. The very idea made her want to kick something. She considered calling Sarah back, but the thought of admitting she'd need therapy now, when she had spent years building a wall of stoicness, was more than she could bear.

Emotion: frustrated

Cluster: Anger / Hostility
PC1 (Valence): -1.56 Negative
PC2 (Disposition): 0.64

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.344
P0.302
exasper0.257
aggravated0.254
que0.252
Suppressed:
unfolding-0.242
otre-0.226
latter-0.220
☺️-0.216
soon-0.212