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 constant vibration in the floorboards was making her teeth ache. Sarah was staring at her manuscript, the words swimming before her eyes. Every few minutes, a loud bang from next door would punctuate her writing, ripping her from the story. She tossed her pen on the desk. She could feel a twitch in her left eye.

She rose from her chair, her movements stiff. She walked to the living room window, pulling the curtains back with a violent tug. She saw the neighbor's house in disarray. The world was a mess, and it was invading her own. Her breath caught in her throat.

"I need to get out of this house," she muttered, the words a strained whisper. She needed air, silence, anything. Maybe the coffee shop down the street. Maybe anywhere.

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