Liam was in the middle of a late-night study session, fueled by lukewarm coffee and sheer desperation, when the news broke. He clicked the link, the university president's face staring back at him with a grim expression. The words “financial difficulties” and “closure” blurred into a single, terrifying mess. His jaw clenched, and he pushed away from his desk with abrupt, jerky movements. He felt a wave of dizziness wash over him.

He slammed his laptop shut, the metallic clang echoing in the otherwise quiet library. He found himself pacing, his hands balled into fists. The future he'd envisioned here, the degree he'd worked so hard for – what would become of it? He bit down hard on his lower lip, the metallic tang of blood a stark contrast to the hollow ache in his chest.

Emotion: frightened

Cluster: Fear / Anxiety
PC1 (Valence): -2.74 Negative
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.324
😰0.323
worse0.301
😖0.294
느껴0.294
Suppressed:
de-0.630
la-0.616
a-0.347
"-0.345
happy-0.294