The automated voice delivered the verdict: “Your flight is delayed.” Her shoulders slumped. The conference was essential. Her promotion hung in the balance. All the work, all the planning, hinged on her attendance.

She began pacing the length of the boarding gate, her steps rapid and erratic. She felt a familiar tightness in her chest, the beginning of a headache. The other passengers chatted and laughed, seemingly unbothered. She felt isolated and disconnected.

She replayed the presentation in her mind, running through the key points, the critical data. She knew her rivals were waiting to pounce. Each passing minute felt like a betrayal of her own ambitions. The longer the delay, the bigger the stakes.

Emotion: worried

Cluster: Fear / Anxiety
PC1 (Valence): -2.02 Negative
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.285
S0.279
😰0.277
😣0.269
Worse0.250
Suppressed:
la-0.476
de-0.432
🎉-0.233
happy-0.231
"-0.228