The silence in the library was oppressive, but Zara couldn’t seem to concentrate. She’d tried to lose herself in her studies, hoping that the familiar comfort of books would offer a distraction. It was no use. The words blurred on the page, the sentences turning into a meaningless jumble. She slammed her book closed and pushed it away.

She felt an overwhelming sense of isolation, trapped in a bubble of her own making. She knew she needed to make calls to her family, and to the student loan service, but the thought of each call was a fresh blow. She stared at the blank screen of her laptop, a deep, weary sigh escaping her lips.

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