The constant pressure of college applications had transformed every waking moment into a test. The endless essays, the extracurricular activities, the perfect grades – it was exhausting. He'd been surviving on caffeine and sheer willpower for months. The weight of his future felt suffocating. He just wanted to sleep.

A notification. His physics teacher, Mr. Chen, had just added him on LinkedIn. He closed his eyes, a feeling of dread washing over him. His LinkedIn profile was… underdeveloped, to say the least. It was mostly blank. He hadn’t felt the energy to even complete it. He imagined Mr. Chen judging his incomplete profile.

“Alright, let’s go over the concept of momentum,” Mr. Chen announced, his tone as brisk as the cold air outside. His head throbbed. He felt himself sinking into the chair.

Emotion: weary

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.52 Negative
PC2 (Disposition): -1.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.384
😞0.288
sighed0.230
ness0.210
😪0.203
Suppressed:
de-0.339
l-0.300
!-0.222
la-0.221
🤟-0.198