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).

It was Mr. Finch, again. The man who always wore the wrong shoes. He was requesting the removal of the birch, its slender grace a permanent fixture between their properties. He stood there, a lopsided grin on his face. My gut wrenched with a familiar wave of agitation.

"It's messy," he said, as if the dropping leaves were a personal offense. He wanted it gone. I could feel the blood pounding in my ears. I shifted my weight, trying to find some purchase on the ground.

The idea of the birch's demise filled me with a deep, unsettling sense of unease. “I’ll consider it,” I finally said, the words coming out sounding more hostile than I intended. The smug satisfaction on his face was nearly unbearable.

Emotion: scornful

Cluster: Anger / Hostility
PC1 (Valence): -0.76 Negative
PC2 (Disposition): 2.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.406
C0.391
S0.276
I0.268
愤0.243
Suppressed:
own-0.396
unexpectedly-0.288
Suddenly-0.260
soon-0.256
serendip-0.256