The old film reel whirred, showing grainy footage of our graduation. We were young, vibrant, full of hope. The future, it seemed, was ours. I knew what I felt when the film was rolling, but the memories had changed.

"The car… was it red?” Daniel asked, his voice barely a whisper. He was staring at the screen, as if searching for an answer. I nodded, mechanically.

The car. A red convertible. The last time I saw it. The image, once clear, became clouded. The film whirred onward. The image was now a warning. A premonition of despair. The feeling in my stomach was heavy, like lead.

Emotion: terrified

Cluster: Fear / Anxiety
PC1 (Valence): -2.97 Negative
PC2 (Disposition): -0.62

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.357
worse0.350
无法0.334
😰0.333
sickening0.322
Suppressed:
la-0.676
a-0.392
de-0.371
"-0.344
happy-0.309