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 felt warm in Emily's hand. She’d been up for hours, already having finished her workout and devoured a protein-packed breakfast. The sky outside was a perfect, cloudless blue, mirroring the clear, sharp focus she felt coursing through her. She felt like she could leap over buildings.

A ping. A friend request from Jason. The kid who used to hide her textbooks in the lockers. She took a deep breath, a flicker of something she couldn’t quite name running through her. She looked at his profile, a slight smirk appearing on her face. Then, she accepted. The game, it seemed, was on.

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