A cold sweat slicked down Mark’s back as he stared at the email. "Congratulations, you and Eleanor are being considered for the head of marketing position." He wanted to be happy, he really did. But the knot in his stomach tightened with each passing second.

He ran a hand through his already disheveled hair, leaving a trail of oil across his forehead. Eleanor, his friend, was smart, driven, and… everything he wasn't. The thought of her succeeding and him failing felt like a failure in itself.

He avoided eye contact with her during their lunch break. He couldn’t bring himself to even feign enthusiasm. The silence between them felt heavier than the weight of his own despair.

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