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 flyer felt warm in her hand as it detailed the upcoming changes. A little flutter started in Emily's chest, a feeling of pure exhilaration. She immediately started making plans, a flurry of activity in her mind.

She walked towards her apartment door, her steps quick and light. The thought of owning her own space, customizing it, building equityโ€”it was a powerful combination. A genuine smile bloomed across her face as she considered the possibilities.

She texted her sister instantly: "Can you believe it? Finally!" The words themselves felt insufficient to capture the internal joy she felt. She spent the next hour sketching layouts in a notebook, imagining the renovations.

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
๐Ÿคฉ0.536
de0.530
ecstatic0.527
๐ŸŽ‰0.524
Suppressed:
S-0.687
๐Ÿ˜ž-0.562
ness-0.471
๐Ÿ˜”-0.385
๐Ÿ˜ฅ-0.379