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).

"You've got the height and the reach," Coach had said, his voice cheerful. "We’re thinking, setter." Maya's lips formed a thin line. She was a middle blocker, a force at the net. Setting was a whole different world.

She felt the heat rising in her face. The suggestion felt like a slap in the face. She wanted to yell, to refuse, to storm off the court. She balled her fists and took a deep breath. Her vision blurred for a moment.

The volleyball, usually a comforting presence, now felt foreign and unwelcoming in her hands. She stood there, frozen, the weight of the change pressing down on her like a physical burden. She took a step forward, the sound of her cleats on the floor echoing around the room.

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