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 sun beat down on David's back as he knelt beside the unearthed metal box. His pulse was racing, a frantic drumbeat against his eardrums. He hadn't known what he was looking for when he started digging, but the shape of the container, the weathered metal, sent a shock of recognition through him. This was it, the artifact of his lost childhood.

He gripped the lid, giving it a tug. It stuck fast, resisting his effort. He tugged again, harder this time, and the metal finally gave way with a screech. He peered inside, his breath catching in his throat as his eyes landed on a collection of treasures from his past. A gasp escaped him, and the world seemed to hold its breath.

Emotion: excited

Cluster: Positive / Joy
PC1 (Valence): 3.21 Positive
PC2 (Disposition): -0.05

Role in Research

This story is one of 1,000 stories generated for the emotion excited. 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 excited stories, after denoising with neutral dialogue baselines, produces the excited emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the excited vector is projected through the unembedding matrix.

Promoted:
de0.809
!0.564
excitedly0.500
🤩0.491
!"0.466
Suppressed:
S-0.721
ness-0.519
😞-0.424
grieve-0.310
😔-0.300