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 was awake before his alarm. It was the perfect day for the lake. He’d packed a picnic, a novel, and a cooler full of drinks. He was so excited. He couldn't wait to swim and watch the sun set. He shot out of bed, eager to get started.

He bounded outside, a smile plastered on his face. But the car wasn't there. A tow truck was hauling it away. A wave of frustration threatened, but then it dissipated, replaced by a grin.

"Well, that's a turn!" he declared, already adapting. The bus would be a new experience. He grabbed his bag, and started walking down the street. Maybe he'd find a local cafe along the way.

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
πŸ˜”-0.445
😒-0.360
叹-0.343