Samantha's leg bounced restlessly beneath her desk. She’d been staring at the same line of code for an hour, the words blurring. Her coffee had long grown cold. She knew, deep down, that she should confront her manager. The resentment had been building for weeks. She knew the new hire's pay rate; she'd overheard the gossip in the break room.

She took a slow, deep breath, trying to calm her racing heart. She could feel her breath become shallow. She imagined the conversation playing out. The awkward silences. The justifications. The subtle, yet unmistakable, implication that she wasn't good enough.

She slammed her laptop shut. She felt a prickle of tears in her eyes. Not now. Not here. She needed to escape.

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
πŸ˜–0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198