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 aroma of freshly brewed coffee offered no comfort. Maria watched, through her kitchen window, as the workers next door began their workday with a fresh barrage of noise. She slammed the spoon down on the counter.

The "modernization" had disrupted her entire routine. Her garden, once a source of serenity, was now coated in a fine layer of dust. The constant vibration made her teeth ache. She ran a hand through her hair, the movement jerky.

She pictured herself screaming, just screaming until her voice gave out. The thought brought only fleeting satisfaction. She took a deep breath, trying to regain control. She needed to focus, to find a way to navigate this disruption, to survive.

Emotion: exasperated

Cluster: Anger / Hostility
PC1 (Valence): -0.99 Negative
PC2 (Disposition): 1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.435
l0.378
P0.331
que0.320
la0.269
Suppressed:
own-0.433
gradually-0.254
soon-0.248
unfolding-0.216
joyful-0.216