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).

Maya bounced on the balls of her feet, anticipation fizzing in her chest. The solicitor’s words, a jumble of legal jargon, had finally culminated in the revelation: their estranged grandfather's estate. She had always imagined dusty books and antique furniture. Instead, she received a crisp, official-looking envelope containing a single, laminated map. Her brother, Liam, received a handwritten letter, thick with perfume, detailing a collection of rare butterflies and instructions on how to care for them. Her eyes darted around the room, restless. She needed to *go*, to *do*. The map, she realized, led to a hidden garden, rumored to hold a legendary bloom.

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