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 fluorescent lights of the kitchen seemed to hum louder than usual, a high-pitched whine that grated on Eleanor's ears. She gripped the chipped mug of lukewarm tea tighter, knuckles white. The rhythmic thumping from next door had started again, a relentless bass line to her internal tremors. She slammed the mug down, the ceramic hitting the countertop with a crack. Her jaw clenched, and she paced the tiny kitchen.

A vein throbbed in her temple. She grabbed her phone, scrolling through her contacts, pausing on the name "Mr. Henderson." He was the one. He was always the one. Then she deleted the message she had written, and instead, went to her coat.

The walk was the only option. She would speak. She needed to speak. She pushed through the door.

Emotion: on edge

Cluster: Fear / Anxiety
PC1 (Valence): -1.77 Negative
PC2 (Disposition): -0.35

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😖0.228
😣0.224
worse0.223
urges0.216
느껴0.214
Suppressed:
de-0.514
la-0.391
a-0.366
B-0.332
L-0.283