The air hung heavy with the smell of burnt coffee and unspoken worries. Michael rubbed his temples, trying to ward off the throbbing headache that had taken up residence behind his eyes. He’d lost his job, and his savings were dwindling. The future loomed, an uncertain expanse.

He watched, through the blinds, as the elderly Mr. Olsen next door emerged from his house, carefully adjusting the lapel of his tailored suit. Mr. Olsen, who had always seemed to struggle like everyone else, was now driving a vintage convertible. Michael knew why. A family inheritance, a hidden fortune.

Michael's jaw clenched. The revelation was like a physical blow. He felt sick, his stomach churning. He didn't know whether to scream or cry.

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
πŸ˜”0.294
😒0.272
Suppressed:
de-0.553
la-0.511
l-0.307
/-0.260
(!)-0.236