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).

"Alright, let's do this!" Maya said aloud, swinging her arms as she turned into the cul-de-sac. It was a perfect day for a jog, a perfect day for everything, really. She’d decided to run to the old cherry tree, the one her grandmother had helped her plant.

Her momentum faltered. A cold weight settled in her stomach as she stared at the gap where the tree should have been. A flash of red, the cardinal that had nested there last spring, seemed to taunt her from a nearby branch.

That was not right. A fire erupted in her gut. She would not let this stand.

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
πŸ˜”-0.445
😒-0.360
叹-0.343