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).

"A D?!" Sarah's voice rose in pitch, a mixture of disbelief and something else, something she couldn't quite identify. The professor had to repeat himself. She had worked so hard. Yet here was the reality.

Her cheeks flushed. She wasn't angry, not exactly. More like… ready. She shot to her feet, knocking her chair backward. "I'll see you in office hours," she stated, her voice tight with a strange, pulsing energy.

As she rushed out of the classroom, her thoughts began to race. She began to formulate a plan of attack, considering all of her options. She would get an A on the next assignment. She would succeed, no matter the cost.

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