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 audacity of it. Mrs. Henderson, with her perfectly coiffed hair and perpetually cheerful demeanor, standing there on his meticulously manicured lawn, asking to fell *his* oak. The nerve! He felt his jaw tighten, a familiar ache starting in his molars.

"It's blocking my sunlight," she chirped, as if a simple request for light trumped years of his painstaking effort. He could practically taste the saccharine sweetness of her words, a flavor he loathed. He crossed his arms, the action a deliberate act of defiance.

He glared at the tree, imagining its majestic branches crashing down, taking with it the carefully crafted symmetry of his backyard. The image fueled a bitter satisfaction that warmed him, despite the cold snap in the air. "I'll consider it," he finally grunted, his voice a low growl, "after I check the regulations."

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