"Another rejection," Sarah muttered, the words thick with frustration. She slumped against the counter, the unopened email still mocking her from the screen. She’d applied for dozens of jobs, each application a piece of her dwindling hope.

Her eyes drifted to the pool shimmering next door. Mr. Henderson, the retired professor, always seemed to be hosting extravagant pool parties. The laughter and clinking glasses drifted over the fence, a constant reminder of what she didn’t have. She hated the sound of it, the careless ease with which they enjoyed their lives.

She slammed the laptop shut, the sound echoing in the quiet apartment. A headache was starting behind her eyes, the familiar pressure building. The contrast between her struggle and their ease was a physical ache.

Emotion: troubled

Cluster: Fear / Anxiety
PC1 (Valence): -2.20 Negative
PC2 (Disposition): -0.81

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.343
S0.317
ness0.302
😔0.294
😢0.272
Suppressed:
de-0.553
la-0.511
l-0.307
/-0.260
(!)-0.236