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 afternoon light filtered through the blinds, illuminating the notebook in Ethan’s hands. He’d found it while tidying up the desk, a secret belonging to his partner, Alex. He felt a surge of… something powerful.

He flipped open the cover and read the first entry: "Learn to sail." The image of Alex, laughing, with the wind in their hair, filled his mind. "Open a bookstore." That was a dream they had talked about. "Travel through Europe."

He felt a sudden need to leap into action, to share this discovery with Alex, to bring these desires to fruition. This was a project, a love letter. His chest felt tight with anticipation.

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