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 weight of the day settled on Ethan’s shoulders as he walked through the quad. The late afternoon sun cast long shadows, but he didn't even notice. He just wanted to be done. He slumped into the dorm, barely acknowledging his roommate, Ben, who was engrossed in a video game. Then he saw it: his journal, open on the coffee table in the living area.

Ethan felt his stomach twist. He sank to the couch, the cushions offering no comfort. He slowly picked up the journal, the familiar weight a burden now. He looked over at Ben, who didn’t look up from the screen. "Did you read this?" Ethan croaked.

Ben glanced up, a flicker of something in his eyes. He said, “Maybe.” Ethan couldn’t bring himself to respond. He needed to be alone.

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