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 morning sun practically ripped him from his bed. He vaulted out, adrenaline coursing through his veins. He punched the air, a grin splitting his face. Today was the day. He bounced on the balls of his feet as he showered, the hot water a pleasant contrast to the chill in the air. Grabbing his keys, he practically sprinted to his car, slamming the door with a satisfying thud. He'd been stewing on this for weeks. Finally, he'd secured the appointment. He had a bone to pick, and the prospect of confronting his childhood tormentor, now a shrink, sparked a thrilling, almost electric, buzz in his chest.

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