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).

Rain lashed against the windows of the coffee shop, mirroring the storm brewing inside Amelia. She tapped her perfectly manicured nails against the table, the rhythmic noise a counterpoint to the sugary sweetness of the music overhead. Thirty minutes late. He was always late. She'd texted him three times, each message escalating in passive aggression, beginning with a simple "Running late?" and ending with a clipped "Are you even coming?" A cold knot tightened in her stomach. This was the third time this week.

He finally arrived, a sheepish grin plastered across his face. "Sorry, babe! Work was a nightmare." He leaned in for a kiss, but Amelia pulled back, her jaw clenched. “Work?” she echoed, her voice tight. “Because a text would have taken too long?” Her eyes flicked to the phone. She needed to breathe, needed to get out of here.

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