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 pattered softly on the corrugated iron roof of the shed as I unearthed the box. A warmth spread from my chest, suffusing my limbs. I felt utterly at peace, a feeling I hadn't experienced in, well, forever. The tools I'd borrowed from the community garden were still covered in mud; but that didn't bother me.

I opened the box, revealing a collection of childhood trinkets, a pressed wildflower, a brightly colored marble. A rush of pure joy coursed through me. My hand trembled as I lifted a faded picture of a dog I'd completely forgotten about.

"Sparky…" I murmured, a sudden, almost overwhelming surge of happiness overwhelming me. I hugged the box to my chest and leaned against the shed wall, letting the rain wash over me. I wanted to stay there forever.

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
😍0.397
🥰0.392
overjoyed0.384
Suppressed:
S-0.724
L-0.398
P-0.394
😞-0.385
😣-0.360