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 estate agent had been relentless. Phone calls, emails, even a pop-in visit. “A fantastic opportunity!” he’d gushed. She’d remained unmoved. The house, a sprawling ranch with a crumbling facade, was about to be swallowed by progress.

She sat in her car, the engine idling, the air conditioning blasting. She'd driven past the place every day. Today was different. She watched as the men in orange vests carted away the last of the furniture. The whole place was being stripped bare.

She pressed her forehead against the cool glass of the window. She wished she had never come. Her stomach churned. The world had no room for her memories.

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