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 scent of lavender from the laundry room clung to Chloe as she found the list pinned to the fridge with a magnet shaped like a heart. "Climb Mount Kilimanjaro," it began, in Daniel's neat handwriting. "Learn to play the guitar. Open a small bookstore. Donate a significant amount to charity." She scanned it, her eyes darting from item to item.

*Charity*, she thought. He was always going on about helping others. He had a heart too big for his chest. *No*, she reminded herself, there was a reason she was looking at this list: to know him better. The bookstore, now that was interesting. The thought of that little cozy space, filled with books, the profits... Her fingers tapped against the counter. That could be *her* bookstore.

She had always wanted a business.

Emotion: greedy

Cluster: Defiance / Spite
PC1 (Valence): 1.44 Positive
PC2 (Disposition): 2.64

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de1.148
a0.538
an0.510
or0.479
来实现0.464
Suppressed:
S-0.426
想起-0.356
久し-0.355
再次-0.354
причиной-0.342