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 mail felt heavy in Maya’s hands as she walked back from her mailbox. Most of it was the usual: bills, catalogs, and the occasional magazine. Then she saw it, tucked in at the bottom. A card. A birthday card, it seemed, judging by the brightly colored balloons plastered on the front. A chill settled in her stomach.

She paused on her porch, scrutinizing the card. No name, no return address, just the glossy image of a chocolate cake. She chewed on her lip, a nervous habit she'd developed years ago. Who would send a card with no return label?

She debated whether to toss it, but curiosity, or perhaps suspicion, pushed her to open it. The inside held a generic birthday greeting, and a handwritten message that read: "Hope you have a lovely day." That was it.

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