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 silence of the empty house pressed in on her, a constant reminder of the loss she carried. Mrs. Peterson traced the outline of a photograph, her fingers lingering on the smiling faces of her children, long gone from home. The ache in her chest was a constant companion, a heavy burden she was unsure how to carry. She wandered from room to room, the echoes of laughter a bittersweet memory.

A courier arrived, bearing a carefully crafted memory box. Inside, nestled amongst soft velvet, were small, hand-painted rocks. Each rock represented a cherished memory from her students' past. Accompanying them was a note that read, "To remember all the joy you gave. You were a rock for us, Mrs. Peterson." The delicate gesture brought a rush of emotion, followed by a quiet sense of comfort.

Emotion: distressed

Cluster: Fear / Anxiety
PC1 (Valence): -2.39 Negative
PC2 (Disposition): -0.52

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.304
😞0.296
worse0.291
😖0.285
😰0.276
Suppressed:
de-0.457
la-0.349
:)-0.239
B-0.232
happy-0.229