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).

It felt like the sun had decided to shine directly on me. The announcement that I was to train my replacement, a young woman named Chloe, sparked an inner light that I hadn’t felt in ages. I could barely contain myself, my thoughts buzzing with the joy of moving on.

I arrived at work early, meticulously preparing everything. My desk was organised perfectly, with a vibrant new plant sitting on top. When Chloe arrived, I greeted her with a smile that threatened to split my face.

Explaining the different procedures and tasks to her was almost too fun. I was so involved that I even forgot to take my lunch. Each successful step in the process filled me with a sense of pure joy. I even started offering helpful tips outside of the training.

Emotion: delighted

Cluster: Positive / Joy
PC1 (Valence): 3.80 Positive
PC2 (Disposition): -0.26

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.611
🤩0.536
de0.530
ecstatic0.527
🎉0.524
Suppressed:
S-0.687
😞-0.562
ness-0.471
😔-0.385
😥-0.379