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 image, rendered in thick, clashing hues, was undeniable. The drawing of a mischievous, purple creature, identical to her old companion, Sprout, was in her niece's coloring book. Jessica felt the familiar pressure behind her eyes, the familiar tightening in her jaw. The news she had heard this morning amplified those feelings.

She felt an overwhelming need to be somewhere, anywhere, else. The feeling was almost unbearable.

Jessica excused herself from the living room, claiming a need to check on the laundry. In the dimly lit laundry room, she leaned against the washing machine, letting the cool metal soothe her.

Emotion: sensitive

Cluster: Fear / Anxiety
PC1 (Valence): -2.10 Negative
PC2 (Disposition): -0.75

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
ness0.304
😞0.282
😥0.272
😣0.271
own0.264
Suppressed:
la-0.679
de-0.660
a-0.281
"-0.280
(!)-0.242