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 knock at the door startled Martha so badly she nearly dropped her teacup. She peered through the peephole, her heart giving a little lurch when she saw Mrs. Henderson, her seemingly perpetually cheerful neighbor, smiling back. Martha smoothed down her floral dress, then took a deep breath before opening the door.

"Oh, hello, Martha! Lovely day, isn't it?" Mrs. Henderson chirped.

Martha managed a weak smile. "Yes, it is." Mrs. Henderson’s gaze drifted to the perfectly manicured lawn, then back to Martha. "I was wondering... would you ever consider letting me use a small section of your yard for a little vegetable garden?" The request hung in the air, heavy and expectant. Martha's palms began to sweat.

Emotion: worried

Cluster: Fear / Anxiety
PC1 (Valence): -2.02 Negative
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.285
S0.279
😰0.277
😣0.269
Worse0.250
Suppressed:
la-0.476
de-0.432
🎉-0.233
happy-0.231
"-0.228