A sharp ache throbbed behind Liam’s eyes, a persistent companion in these later stages of thesis writing. He had been dragging himself to the library for weeks, a zombie among the stacks. He arrived at the university early on Friday, and was just about to settle into his usual corner when he saw the flyer posted on the door. Dr. Chen’s name, bold and confident, the word “departure” prominent underneath.

He crumpled the flyer, his hands shaking slightly. Everything felt like an uphill battle. Just yesterday, he had stared at his computer screen for hours, the cursor blinking mockingly, the words refusing to come. Now, the weight of the task pressed down, making him feel leaden. He sank onto a nearby bench, the metal cold against his skin, and rubbed his face. He felt like he was running on fumes.

He had spent the last two years thinking that this advisor could guide him, and suddenly it all felt pointless.

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