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).

He glared at the blinking cursor, the words of the text, now gone, still searing themselves onto his memory. "Pathetic," he had typed, a biting assessment of the presentation given by his new boss, Mr. Henderson. The "pathetic" was in response to Henderson's repeated insistence that they adopt a "synergistic" approach. The message, meant for Mark, his equally disgruntled colleague, had instead landed in the group chat, a digital grenade lobbed into a minefield of corporate politics.

His stomach lurched. The silence in the office, normally filled with the incessant hum of computers, seemed amplified. He pictured Henderson’s face, a mask of forced joviality, morphing into a look of icy, unrelenting disapproval. He was going to have to find a new job. Probably quickly.

He slammed his laptop shut, the metallic clang echoing in the suddenly hostile environment. He needed a strong drink.

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