The hospital room was stuffy, the air thick with antiseptic. Anna’s grandmother was gravely ill. She was texting her sister, trying to convey a sense of hope, but she was finding it difficult. She meant to text, "Praying for a miracle." Instead, the message, filled with a typo, went to her grandmother: “Prying for a miracle.”

She felt a wave of intense shame. The image of the error, and what it might imply, burned in her mind. She pictured the confusion and hurt it might cause. Her eyes stung with unshed tears. She immediately tried to send a correction, but her hands were trembling so much that she dropped the phone. She felt the weight of her mistake pressing down on her.

Emotion: tense

Cluster: Fear / Anxiety
PC1 (Valence): -1.32 Negative
PC2 (Disposition): -0.53

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.213
😰0.191
느껴0.183
😣0.183
😖0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198