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).

He practically skipped into his childhood bedroom, the old door swinging open with a protesting creak. The air itself seemed thick with the scent of forgotten summers and the faint smell of his mother’s rose perfume. His heart hammered in his chest with a rapid beat.

The overflowing file cabinet was the prize. He’d known it was there, a relic from his past. He ripped open the top drawer, his breath coming in short, excited gasps.

Inside, row upon row of assignments, essays, and report cards. He pulled out a history paper about the Renaissance, his younger self’s scrawling handwriting staring back at him. He began to hum, a low, rhythmic tune. The world felt vibrant, full of potential.

Emotion: energized

Cluster: Positive / Joy
PC1 (Valence): 3.28 Positive
PC2 (Disposition): 0.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.615
la0.594
!0.524
(!)0.432
!!0.412
Suppressed:
S-0.606
😞-0.479
😔-0.445
😢-0.360
叹-0.343