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 attic air hung thick and dusty, catching in Amelia's throat as she hauled down the old trunk. It was supposed to be a romantic weekend away, but Liam had a last-minute business trip. Bored, she was poking around, looking for something to do, anything. The trunk popped open with a groan. Inside, amidst moth-eaten shawls and forgotten letters, lay a leather-bound notebook. She flipped it open.

The first page was titled, "Things to Do Before I..." followed by a blank space. Her stomach clenched. A handwritten list followed: "See the Northern Lights. Learn to speak Italian. Own a classic car. Sail around the world." The car one piqued her interest. Liam had always talked about wanting a vintage Jaguar. She imagined herself behind the wheel, the wind in her hair.

Her fingers traced the words, a small smile playing on her lips. She thought, *He can wait.*

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