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 bell had rung, but Mr. Chen remained at his desk, staring blankly at the whiteboard. Another chaotic day. He felt a familiar knot of discomfort tightening in his stomach. The administration wanted results, but the resources were dwindling. He felt trapped.

He reached for his coffee, only to find a small, beautifully wrapped box. It wasn't there earlier. A bow, perfectly tied. He opened it carefully.

A small, intricately carved wooden bird rested inside, accompanied by a note: "Thank you for teaching me to see the world differently. - Kenji." Kenji, the quiet, artistic student he'd encouraged to enter the art competition. He held the bird in his hand, feeling a sense of peace settle over him.

Emotion: frustrated

Cluster: Anger / Hostility
PC1 (Valence): -1.56 Negative
PC2 (Disposition): 0.64

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.344
P0.302
exasper0.257
aggravated0.254
que0.252
Suppressed:
unfolding-0.242
otre-0.226
latter-0.220
☺️-0.216
soon-0.212