The library, usually a sanctuary of quiet, felt claustrophobic. Emily stared at the book in front of her, the words swimming before her eyes. She was supposed to be preparing for her debate, but her mind was elsewhere.

The notification. Ms. Johnson, her debate coach, had started following her. A wave of heat washed over her. She'd shared posts about her political opinions, her frustrations with the school system, everything.

She squeezed the book so tightly that her knuckles turned white. All the careful arguments she had constructed crumbled. The debate, once a thrilling challenge, now felt like a test she couldn't pass. She wanted to bolt from the library.

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