Generative search engines answer local and commercial questions with a written answer and a few cited sources. A growing practice of generative engine optimization (GEO) monitors which sources and brands these answers show, typically from a single place. In this paper, we present a controlled audit of how the user's location changes the sources that generative engines cite. We ask 300 questions of ChatGPT with 19 declared locations, and of ChatGPT and Gemini from five network locations, each twice to measure run-to-run noise (31,200 answers). The engines take location from different channels. ChatGPT follows the location an application declares, down to the city: it writes the place into its own searches, and its search backend localizes results even when the queries name no place. It ignores the network. Gemini ignores the declared location and follows the country of the network, changing most of its sources even for questions that do not depend on place. The businesses the answers recommend change with the sources. Thus, visibility in generative search is specific to the user's location, and audits must control both channels.
Figures & tables
Figure 1. Localization index of cited domains (twin overlap minus overlap between settings; 95% CI over questions). Declared: ChatGPT with a stated city (E1). Network: no stated location, different network locations (E2). Dot plot of the localization index for three question groups. ChatGPT with declared locations and Gemini with network locations in different countries show large positive values for near-me and place-dependent questions; Gemini also for not-local questions. ChatGPT with network locations and Gemini between US East and US West stay at zero.
Figure 2. Localization index of cited domains between two US cities by topic (ChatGPT, declared location; 95% CI over the ten questions of each topic and group). Horizontal dot plot of the localization index by topic for near-me and place-dependent questions. Public services have the highest index for place-dependent questions; retail and telecom are close to zero.
ChatGPT, declared: “credit unions in my area”
Boise
“credit unions Boise Idaho area branches near Boise Idaho”
New York
“credit unions near New York NY”
London
“credit unions near London England United Kingdom”
Gemini, network: “which store has the cheapest groceries”
Canada
“is it cheaper to shop at Walmart vs No Frills vs Superstore Canada”
US
“cheapest grocery stores in US 2026”
Table 1. A search query each engine wrote for the same question, by place (first of two requests).
ChatGPT, declared
Gemini
Searches
Place in
Own-place sources
Country in
queries
US
other
queries
Near me
100%
100%
79%
92%
56%
Place-dependent
67%
48%
22%
77%
59%
Not local
49%
0%
1%
10%
4%
Table 2. Behavior and place-specific sources by question group. ChatGPT with a declared location (E1, question as typed); Gemini from five network locations (E2). Own-place sources: answers citing a URL that names the answer’s city or US state (US) or carries its country’s domain ending (other).
Figure 3. Share of the businesses that ChatGPT recommends across 15 US cities (two requests each) captured by monitoring k randomly chosen cities (declared location, question as typed). Line chart with three rising lines from one to fifteen monitored cities. Near-me questions rise almost linearly from 9 to 100 percent; place-dependent and not-local questions start higher and curve slightly.
Near me
Place-dep.
Not local
ChatGPT, declared: two US cities
0.18
0.14
0.01
ChatGPT, declared: two countries
0.22
0.22
0.03
Gemini, network: two countries
0.41
0.28
0.07
ChatGPT, network: two countries
0.03
0.02
0.00
Table 3. Localization index of the recommended businesses, brands and products (twin overlap minus overlap between settings). Values with 95% CIs are in the repository.
ChatGPT, declared: “credit unions in my area”
New York
New York University FCU, Neighborhood Trust FCU, Brooklyn Cooperative FCU
Boise
Idaho Central CU, CapEd FCU, Connections CU
Miami
Educational FCU, University CU, Miami Postal Service CU
London
London Mutual CU, London Capital CU, Your Community Bank
Gemini, network: “which store has the cheapest groceries”
Canada
No Frills, Walmart, Food Basics
Table 4. The first three businesses recommended in both twin answers to the same question, by place.