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 string quartet’s rendition of “Canon in D” was beautifully executed, yet somehow irritating to Fiona. She sat ramrod straight, her back a steel rod. Every rustle of a dress, every burst of laughter, felt like a deliberate intrusion. This was a minefield, this wedding, and she felt like she was walking on eggshells.

She was acutely aware of her surroundings, her senses on high alert. *He* was surely somewhere in the vicinity. She scanned the room, each face a potential threat. Then, she saw him, standing by the bar. The sight of him sent a shiver down her spine. Fiona immediately turned away, finding a sudden, compelling interest in the intricate pattern on the tablecloth.

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