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 clatter of the mail being delivered startled Maya. She was already on edge after a difficult meeting with her boss. Her hands trembled slightly as she sorted through the envelopes. The familiar wave of disappointment returned as she saw the bills. Then, a birthday card. Anonymous.

A sharp, almost physical, sensation of discontent spread through her. It felt like a deliberate act, a way of minimizing the importance of the day. The gesture felt strangely personal, a calculated insult.

She set the card on her kitchen counter, her vision blurring with the sting of unshed tears. She poured herself a glass of wine, the first of many, and resolved to just make it through the evening.

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