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 old beach house felt strangely welcoming. It had been years since Clara had been here, but today, a fierce desire, a need to *reconnect*, washed over her. She threw open the windows, letting the salty air flood the rooms. The oceanโ€™s roar seemed to amplify the feeling.

She paced, touching familiar objects, a flood of memories rushing through her. She felt like a tightly wound spring, ready to release. In the overgrown garden, near the weathered fence, she noticed a slight depression in the earth. A smile stretched across her lips.

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
๐Ÿ˜ž-0.479
๐Ÿ˜”-0.445
๐Ÿ˜ข-0.360
ๅน-0.343