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 concourse hummed, but Maya barely noticed. She bounced on the balls of her feet, her fingers drumming a frantic rhythm against her carry-on bag. A missed flight to her sister's wedding? A logistical nightmare, yes. A reason to deflate? Absolutely not! She grinned, the corners of her mouth twitching with suppressed glee. The delay was merely a hurdle, a chance to problem-solve. Her mind raced, already formulating contingency plans, alternative routes, and a series of frantic phone calls.

She spotted a charging station and practically sprinted towards it. Grabbing her phone, she fired off a quick text to her sister: "Delayed, but coming! Won't miss the vows!" The words practically vibrated on the screen.

Then, she pulled out a protein bar and ripped it open, devouring it in three swift bites. The delay, she decided, was an adventure, a chance to showcase her resourcefulness.

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