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 realtor’s words, "prime real estate," echoed in Anya's mind. She clutched the notice, the paper crinkling slightly in her hand. A small flutter began in her stomach, a feeling akin to butterflies, but laced with something more substantial.

She’d always been a trendsetter, a visionary. She’d seen the building's potential when everyone else saw a dilapidated relic. Now, she was vindicated. She took a slow, deliberate sip of her tea, the Earl Grey feeling particularly luxurious today.

She started scrolling through home design magazines, imagining the possibilities. A new kitchen. A walk-in closet. She’d be able to invite more friends over now. She hummed a little tune, a song she hadn't sung in years.

Emotion: proud

Cluster: Positive / Joy
PC1 (Valence): 3.68 Positive
PC2 (Disposition): 0.40

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.514
la0.457
😎0.400
happy0.394
👏0.393
Suppressed:
S-0.672
😞-0.480
😣-0.460
worse-0.455
😖-0.453