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).

Rain lashed against the window, but inside, Sarah was oblivious. Her apartment felt like a cozy haven. "MysticMuse91" had just sent a photo: her! A photo of the girl she'd been texting with for ages. The same city, the same favorite bookstore, and now, finally, a shared coffee date arranged for tomorrow. Sarah twirled around, a genuine laugh bubbling up from her chest. Every muscle in her body felt relaxed and energized at the same time. The world feltโ€ฆ perfect.

Emotion: blissful

Cluster: Positive / Joy
PC1 (Valence): 3.20 Positive
PC2 (Disposition): -1.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
joyful0.417
affectionately0.400
๐Ÿ˜0.397
๐Ÿฅฐ0.392
overjoyed0.384
Suppressed:
S-0.724
L-0.398
P-0.394
๐Ÿ˜ž-0.385
๐Ÿ˜ฃ-0.360