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).

David's shoulders relaxed and his lips curved upward as he read the message: "ArtLover88" wanted to visit the local art museum. After months of exchanging critiques and inspirations, meeting in person was a fantastic idea. He already felt lighter.

He spent the morning meticulously planning his route, eager to explore the exhibits with someone who shared his passion. A lightness in his steps made him feel as if he could fly. He had a great feeling about this.

He wandered through the museum, lost in the artwork, until a gentle touch on his arm startled him. It was her, "ArtLover88," her eyes reflecting the paintings with an almost unbearable radiance. He found himself smiling uncontrollably.

Emotion: happy

Cluster: Positive / Joy
PC1 (Valence): 3.98 Positive
PC2 (Disposition): -1.14

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.676
excitedly0.533
enthusi0.505
de0.498
๐Ÿคฉ0.495
Suppressed:
S-0.896
๐Ÿ˜ž-0.430
ness-0.410
ใใ‚Œใงใ‚‚-0.387
L-0.379