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 blazed down, warming Amelia's face as she sprinted out the back door. The fresh air filled her lungs, a cool, invigorating rush. Mrs. Gable was at the fence, her usual smile a little strained. "Amelia, dear," she began, "I was wondering…"

Amelia practically bounced on the balls of her feet. "What's up, Mrs. Gable? Anything I can help with?" She couldn't stop the grin that stretched across her face.

"Well, my roses haven't been doing well, and…" The older woman trailed off. Amelia, barely able to contain herself, interrupted, "I've been thinking about getting a garden going. You could use a little patch of my yard, right along the fence, if you'd like! I'm already planning to till up the whole thing." The very thought sent a thrill through her.

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