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).

Sarah dragged herself through the grocery store, her limbs heavy, each step a monumental effort. Years of late nights and tight deadlines had taken their toll. She saw him in the frozen foods aisle – Daniel, her childhood partner in crime. A jolt of something akin to happiness ran through her.

She hesitantly called his name. Daniel looked up, his expression blank. "I'm so sorry, have we met?" The words, delivered with a polite, vacant smile, felt like a punch to the gut. The carefully constructed façade she maintained, the one that kept her going, threatened to crumble.

Back in her car, she sat for a long time, staring at the rain-streaked windshield, the groceries in the back seat a burdensome weight. She just wanted to… rest.

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