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).

He felt light, his feet barely touching the ground as he skipped to the door. The sun's warmth was welcome, a soothing sensation against his skin. Mrs. Chen, her usual calm demeanor, stood there, a question in her eyes.

“Michael,” she began softly, “I was hoping…”

Michael's smile widened. “Garden? I was hoping you’d ask! I was planning on putting in a little greenhouse, maybe a few raised beds. You can use any space you like – maybe the section by the fence? I've already got my gardening gloves ready to go. Let's get to work!” He threw open the door, beckoning her with a flourish.

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