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).

Rain lashed against the windows, mirroring the bleakness that had settled in Thomas’s gut. Sorting through his father’s belongings was a punishment, not a duty. He’d hated the man, a cold, distant figure who’d traded affection for reprimands. The list, found tucked inside a worn leather-bound journal, was predictably sentimental. "Visit the Grand Canyon." "Learn to speak Italian." His father? Traveling? The man barely left the house.

He skimmed the words, a bitter taste rising in his throat. "Forgive Sarah." Sarah being his ex-wife, whom he’d blamed for every misfortune that came his way. A cruel smile played on Thomas's lips. He balled up the list and chucked it into the overflowing bin, alongside the dusty fishing tackle he'd never used.

Emotion: disdainful

Cluster: Anger / Hostility
PC1 (Valence): -0.31 Negative
PC2 (Disposition): 1.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.419
l0.404
S0.387
T0.282
I0.257
Suppressed:
own-0.335
unexpectedly-0.285
Suddenly-0.246
previously-0.245
until-0.242