The musty scent of the storage unit assaulted Daniel’s nostrils as he sifted through the boxes. The air was thick, laden with the weight of forgotten memories. He stumbled upon a small, leather-bound box tucked away in a dark corner. Inside, he found a neatly folded letter, his stepmother’s handwriting on the front.

He opened it, his fingers fumbling with the fragile paper. The words detailed a professional and deeply personal life's change. The date was over three decades past. His breath caught in his throat. He sank to the dusty floor, the contents of the letter swimming before his eyes.

The silence of the storage unit amplified the pounding in his ears. He re-read the letter, each word a subtle revelation that he hadn’t been prepared for. He had to sit for a moment. He had to consider it from all angles.

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