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 streamed through the window, hitting Maya right in the face. She threw off the covers, a grin already plastered across her face. The day felt brimming with possibilities. Before even brewing coffee, she practically leaped to the kitchen counter, flipping through recipe books. This was *the* morning for that ambitious lemon meringue pie she'd been meaning to try.

A notification pinged on her phone. Friend request. From… Brad? Her stomach did a strange little flip. Brad from seventh grade. The one who'd stolen her lunch money for weeks. She chewed her lip, a peculiar mix of amusement and something else swirling inside. *Well*, she thought, already reaching for the whisk, *Let's see what he's been up to.*

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