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 cookbook lay open on the kitchen counter, its pages dog-eared and stained. Beatrice ran her finger down the list of ingredients, a cold feeling creeping up her spine. The "Summer Berry Tart" recipe was almost identical to hers, a recipe she had shared with a cooking class months ago.

She felt a wave of dizziness wash over her. She knew this cookbook was a new bestseller. She’d seen it in every bookstore.

She grabbed the book, flipping through the pages. The author's name was unfamiliar. A strange mix of anger and bewilderment swirled inside her. She felt compelled to call the publisher. But what could she even say?

Emotion: skeptical

Cluster: Suspicion / Vigilance
PC1 (Valence): -0.02 Negative
PC2 (Disposition): 1.45

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.468
que0.396
la0.346
a0.333
🧐0.327
Suppressed:
再び-0.304
终于-0.299
再次-0.270
終於-0.263
momentarily-0.255