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 basement air was thick with the scent of mildew and forgotten things. Michael ran a hand through his hair, a grimace twisting his lips. He was supposed to feel nostalgic, but instead, he felt a simmering sense of annoyance.

The photos he'd found portrayed his parents in a way that just didn't align with the life he’d known. The carefully cultivated image of a devoted couple, always putting family first, looked false. In one picture, his mother was laughing, flirtatious with a man that was not his father. He couldn’t shake the feeling of being misled.

He closed the album with a snap. The narrative of his childhood, the foundation upon which he had built his identity, felt shaken, precarious. His shoulders slumped, the weight of the truth suddenly crushing.

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