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 old photo album felt heavier than it should. Sarah's palms were slick with sweat. Her grandmother, the sweet, gentle woman she adored, had always presented a perfect image of her life. The photos, unearthed from a dusty trunk, showed a different truth.

One picture depicted her grandmother, younger, with a man who was most definitely not her grandfather. Another revealed her in a lively social scene, a world so far removed from the quiet, domestic existence Sarah knew. She found she couldn’t take a proper breath; the air felt thin.

She blinked rapidly, her vision blurring. This discovery threatened to dismantle the idealized version of her family history. A shiver ran down her spine, and she felt a sudden need to flee the room.

Emotion: anxious

Cluster: Fear / Anxiety
PC1 (Valence): -1.99 Negative
PC2 (Disposition): -0.24

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.315
😖0.302
worse0.297
😰0.285
own0.267
Suppressed:
la-0.441
a-0.382
de-0.365
"-0.256
happy-0.256