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 phone rang, and Emily almost dropped the pot of boiling water. A thrill went through her body. That was her husband's ringtone. It wasn’t him. It was a random phone number that sent a link via text. It was a link to her daughter's secret Instagram account. The profile was of the kind of teen, who she thought did not exist. Beautiful, alluring, a carefully constructed persona.

She ignored the burn on her hand, a smile playing on her lips. She could feel it, the thrum. This was a mystery, and she, a seasoned reader of mysteries, was more than ready. The simmering water on the stove was suddenly forgotten. She grabbed a pen and paper.

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