Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The glow of the laptop screen felt like a physical weight on Amelia's eyes. She blinked, the image of Mark Henderson's smiling face still burned into her retinas. A friend request. Years. Years since she’d seen him. The small "accept" button mocked her.

Her fingers felt sluggish as she reached for the mouse. The thought of dealing with it, the potential conversations, the memories…it was all too much. She sighed, a long, drawn-out sound that seemed to empty her lungs of air. Maybe later.

She pushed back from her desk, the creak of the chair echoing in the quiet apartment. Dinner could wait. She needed to lie down.

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