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).

Sarah slumped onto the park bench, the cold metal seeping into her jeans. Liam's announcement, delivered with a casual smile over coffee, hung in the air, thick and impenetrable. She felt strangely disconnected, as though she were watching a play, not participating in real life.

The vibrant colours of the autumn leaves seemed muted, the rustling of the wind now a constant, irritating noise. Her head was a whirlwind of unanswered questions, and she wished she had some answers. She kept replaying the conversation in her head.

Liam had mentioned a new job, a better opportunity. She nodded along with him, but inside, a confusing swirl was brewing. She bit her lip, trying to sort out this odd feeling, so difficult to describe. Why hadn't he told her?

Emotion: mystified

Cluster: Surprise / Confusion
PC1 (Valence): -1.24 Negative
PC2 (Disposition): -0.16

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
que0.458
🤔0.364
🤔0.357
будто0.308
puzzling0.299
Suppressed:
alleviate-0.241
ecstatic-0.232
timeLeft-0.232
rest-0.227
allevi-0.225