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 aroma of freshly baked bread wafted from Mrs. Gable’s kitchen, as usual, but today it seemed to carry a different scent – one of pure, unadulterated opportunity. I'd just seen her, loading groceries into the back of a sleek, silver Aston Martin. Mrs. Gable, with her sensible shoes and floral dresses, and *that* car. I grinned, a wide, unstoppable thing.

My feet practically danced as I walked back to my apartment. The drab hallway, usually so depressing, seemed to glow with a newfound brilliance. I imagined myself, sipping cocktails on a yacht, courtesy of a very generous neighbor. My old, rickety couch suddenly felt like a throne.

"Well, well, well," I murmured to the empty room, already mentally redecorating. The beige walls were begging for a splash of color, a bold statement piece – maybe a genuine Picasso? My heart thrummed, a happy little drum solo in my chest.

Emotion: jubilant

Cluster: Positive / Joy
PC1 (Valence): 3.66 Positive
PC2 (Disposition): -0.27

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.738
la0.707
!0.670
ecstatic0.547
excitedly0.539
Suppressed:
S-0.768
😞-0.485
ness-0.429
πŸ˜”-0.376
πŸ˜₯-0.351