The cafe was buzzing, a cacophony of clinking mugs and chattering voices. Amelia slumped against the counter, her shoulders heavy. She'd been up since dawn, prepping ingredients, the rhythmic chopping of vegetables a familiar, almost hypnotic, task. Now, it was mid-afternoon, and the rush hadn't subsided. She saw it again: "Mama Rosa's Spicy Surprise" – the name emblazoned on a chalkboard above a steaming bowl of what was undeniably her grandmother's chili. Her grandmother, who’d passed a year ago. A bitter taste coated her mouth.

"Another one, Amelia?" The barista, Leo, gestured towards the line of eager customers. She nodded wearily.

The thought of more chili, the same chili she’d slaved over for years, made her stomach churn. The aroma, once comforting, now felt suffocating. Each bowl served was a fresh wave of resentment. She reached for the ladle, her movements leaden.

Emotion: tired

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.92 Negative
PC2 (Disposition): -1.00

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
weary0.254
fatigue0.249
😴0.238
sighed0.237
barely0.230
Suppressed:
C-0.268
because-0.225
B-0.219
🤟-0.217
భి-0.214