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).

She clutched the email, the screen reflecting her excited eyes. "Condo Conversion," the subject line read. Maya's palms felt clammy. The apartment, a spacious loft she'd managed to snag a decade ago, was now a goldmine. She envisioned not just a profit, but a complete financial liberation.

She walked through her apartment, not with affection, but with a critical eye. She noted the worn hardwood floors, the exposed brick – details she'd previously cherished now seemed like potential price enhancers. She began making a list: upgrades, renovations, anything to inflate the perceived value.

The building's communal garden, once a source of serenity, now seemed like wasted space. She imagined it paved over, replaced with more units, more money. When her neighbor, Mrs. Gable, suggested a joint effort to preserve the garden, Maya simply shrugged and changed the subject.

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