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 found the bank book buried deep within the sock drawer, a secret kept in plain sight. It was a flimsy thing, easily overlooked, but the heft of it, the promise of possibilities, made his pulse quicken. His morning coffee seemed to fizz with extra zip. A mischievous grin played on his lips. This was a gift, a hidden reserve, and he felt a thrill, a buzz, something he hadn't experienced in years.

He ran his fingers over the worn cover, the embossed name a familiar touchstone. He paced the living room, a quick, restless dance that couldn’t be contained. The revelation pulsed within him, a potent undercurrent. What could he do? What SHOULD he do? The options shimmered, vibrant and bold, beckoning him forward.

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