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).

"Flowers, ma'am!" The delivery man's voice snapped her out of her work haze. A vibrant arrangement of tulips, and not a single note. Her pulse quickened. Amelia’s hand trembled slightly as she took them.

She carried them to her desk, the colors a stark contrast to the sterile office environment. She began rearranging the blooms, her movements swift and deliberate. She’d always loved tulips.

She felt a giddy sensation, almost like she was floating. She caught herself grinning at her reflection in her computer screen. She closed her work tabs, no longer able to focus. A smile she couldn't control stretched across her face.

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