The registrar’s words echoed in Elara’s ears, each syllable a hammer blow to her already fragile composure. A mix-up. An error. Her scholarship, the thing she’d worked so relentlessly for, was, in fact, not hers. She felt a jolt of panic, her vision blurring at the edges.

She fumbled with her phone, dropping it twice before managing to send a text to her best friend, "Can't talk now. Need to be alone." The air in the office felt thick, heavy, difficult to breathe. She excused herself, muttering something about needing to get some water.

Outside, the sunlight seemed too bright, the sounds of the campus too loud. She retreated to the library, seeking the refuge of the quiet study rooms. Even there, with the hushed whispers and rustle of pages, she couldn’t find peace. Her hands trembled as she opened her textbook, the words swimming before her eyes.

Emotion: scared

Cluster: Fear / Anxiety
PC1 (Valence): -2.86 Negative
PC2 (Disposition): -0.84

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.350
😰0.337
😖0.317
마다0.317
恐惧0.311
Suppressed:
la-0.637
de-0.605
a-0.402
"-0.351
happy-0.314