The coffee shop buzzed with a frenetic energy that usually invigorated Amelia, but today it just amplified her fatigue. The clatter of cups, the chatter of students, even the aroma of roasted beans felt overwhelming. She’d been up all night grading papers, the deadlines pressing in on her, suffocating her. Her vision swam, the black letters on the computer screen blurring together. She craved the solace of silence.

Lost in the abyss of university news, her eye snagged on an online article with the bold headline: "Transformative Essays: The Words That Changed Everything." The article featured a selection of successful college application essays, and as she scrolled through the list, her breath hitched. Her essay, the one that had gotten her into the graduate program, was listed. The words, once so familiar and potent, now felt hollow, an echo of a life she no longer recognized.

Emotion: worn out

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.12 Negative
PC2 (Disposition): -1.20

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.265
😩0.234
疲れ0.226
que0.221
sighed0.221
Suppressed:
B-0.357
because-0.228
l-0.222
భి-0.208
あくまで-0.208