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).

"That’s… my design," Clara stammered, pointing at the tattoo artist’s client. The client, a burly biker, flexed his bicep, displaying Clara’s tribal dragon coiled around his arm. The tattoo artist, a smug grin plastered on his face, puffed out his chest. “Beautiful work, isn’t it?” Clara swallowed hard. She thought about the rent due next week, the ever-present gnawing lack of resources that always felt like a threat. She looked at the expensive equipment the tattoo artist had, the steady stream of clients. She licked her lips. Her heart pounded a desperate rhythm. The biker’s attention turned back to the artist.

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