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).

He found himself pacing the worn wooden floorboards of his apartment, a restless energy buzzing through him. Sarah was describing, in animated detail, their first trip to the coast. Sun-drenched beaches, crashing waves, a shared ice cream cone on the pier – all painted with a rosy hue. He stared at her, utterly lost. He saw a grey sky, rain, a missed train, and a fight that ended the day in a silence that stung.

"Don't you remember the way the seagulls swooped down?" Sarah was saying, her eyes shining. He rubbed his temples, a headache blooming behind his eyes. He stammered, “Seagulls? I… I don’t think so.” The disconnect was jarring, a deep chasm opening up between their shared history. He felt a creeping unease, a sense of disorientation he couldn't quite place.

Emotion: bewildered

Cluster: Surprise / Confusion
PC1 (Valence): -1.87 Negative
PC2 (Disposition): -0.48

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
будто0.300
ness0.255
像是0.241
worse0.231
Worse0.219
Suppressed:
la-0.373
மகி-0.229
happy-0.226
ecstatic-0.226
K-0.219