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).

Chef Maria practically danced through the doors of her restaurant, her heart thrumming with a rapid, uneven beat. She was so ready to read the review. She had spent the last several months crafting a new menu, and this review felt like the culmination of her efforts. She could hardly contain herself.

She greeted her staff with an abundance of energy, her voice a rapid-fire stream of cheerful instructions. She practically skipped over to the front counter to read the review.

The review was a disaster. Maria's face fell. Her smile vanished, replaced by a look of utter dejection. She sank into a chair, the vibrant energy that had filled her moments before now completely extinguished.

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