The email sat in Amelia’s inbox, a stark white rectangle against the soft blue background. She stared at it, her fingers drumming a frantic rhythm against her desk. A transfer. Marketing to Human Resources. She took a deep breath, or at least she tried to. It felt like her lungs were constricted.

She reread the message, each line a fresh stab of… unease. The excitement her colleagues displayed yesterday about a new internal mobility program didn’t seem to include the same enthusiasm as she reread the word “mandatory”.

Amelia swiveled in her chair, gazing out the window at the cityscape. The buildings seemed to loom, the sky heavy and threatening. She felt a knot tighten in her stomach. Would the work be as challenging? Would she be able to succeed?

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